Tootfinder

AIM: Amending Inherent Interpretability via Self-Supervised Masking
Eyad Alshami, Shashank Agnihotri, Bernt Schiele, Margret Keuper
https://arxiv.org/abs/2508.11502 https://

AIM: Amending Inherent Interpretability via Self-Supervised Masking
It has been observed that deep neural networks (DNNs) often use both genuine as well as spurious features. In this work, we propose "Amending Inherent Interpretability via Self-Supervised Masking" (AIM), a simple yet interestingly effective method that promotes the network's utilization of genuine features over spurious alternatives without requiring additional annotations. In particular, AIM uses features at multiple encoding stages to guide a self-supervised, sample-specific feature-masking p…

V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models
Qidong Wang, Junjie Hu, Ming Jiang
https://arxiv.org/abs/2509.14837

V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models
Recent advances in causal interpretability have extended from language models to vision-language models (VLMs), seeking to reveal their internal mechanisms through input interventions. While textual interventions often target semantics, visual interventions typically rely on coarse pixel-level perturbations, limiting semantic insights on multimodal integration. In this study, we introduce V-SEAM, a novel framework that combines Visual Semantic Editing and Attention Modulating for causal interpr…

Model Interpretability and Rationale Extraction by Input Mask Optimization
Marc Brinner, Sina Zarriess
https://arxiv.org/abs/2508.11388 https://arxiv.org/p…

Model Interpretability and Rationale Extraction by Input Mask Optimization
Concurrent to the rapid progress in the development of neural-network based models in areas like natural language processing and computer vision, the need for creating explanations for the predictions of these black-box models has risen steadily. We propose a new method to generate extractive explanations for predictions made by neural networks, that is based on masking parts of the input which the model does not consider to be indicative of the respective class. The masking is done using gradi…

Towards Faithful Class-level Self-explainability in Graph Neural Networks by Subgraph Dependencies
Fanzhen Liu, Xiaoxiao Ma, Jian Yang, Alsharif Abuadbba, Kristen Moore, Surya Nepal, Cecile Paris, Quan Z. Sheng, Jia Wu
https://arxiv.org/abs/2508.11513

Towards Faithful Class-level Self-explainability in Graph Neural Networks by Subgraph Dependencies
Enhancing the interpretability of graph neural networks (GNNs) is crucial to ensure their safe and fair deployment. Recent work has introduced self-explainable GNNs that generate explanations as part of training, improving both faithfulness and efficiency. Some of these models, such as ProtGNN and PGIB, learn class-specific prototypes, offering a potential pathway toward class-level explanations. However, their evaluations focus solely on instance-level explanations, leaving open the question o…

RadarQA: Multi-modal Quality Analysis of Weather Radar Forecasts
Xuming He, Zhiyuan You, Junchao Gong, Couhua Liu, Xiaoyu Yue, Peiqin Zhuang, Wenlong Zhang, Lei Bai
https://arxiv.org/abs/2508.12291

RadarQA: Multi-modal Quality Analysis of Weather Radar Forecasts
Quality analysis of weather forecasts is an essential topic in meteorology. Although traditional score-based evaluation metrics can quantify certain forecast errors, they are still far from meteorological experts in terms of descriptive capability, interpretability, and understanding of dynamic evolution. With the rapid development of Multi-modal Large Language Models (MLLMs), these models become potential tools to overcome the above challenges. In this work, we introduce an MLLM-based weather …

Neural Earthquake Forecasting with Minimal Information: Limits, Interpretability, and the Role of Markov Structure
Jonas Koehler, Nishtha Srivastava, Kai Zhou, Claudia Quinteros, Johannes Faber, F. Alejandro Nava
https://arxiv.org/abs/2509.14661

Neural Earthquake Forecasting with Minimal Information: Limits, Interpretability, and the Role of Markov Structure
Forecasting earthquake sequences remains a central challenge in seismology, particularly under non-stationary conditions. While deep learning models have shown promise, their ability to generalize across time remains poorly understood. We evaluate neural and hybrid (NN plus Markov) models for short-term earthquake forecasting on a regional catalog using temporally stratified cross-validation. Models are trained on earlier portions of the catalog and evaluated on future unseen events, enabling r…

Learning Mechanistic Subtypes of Neurodegeneration with a Physics-Informed Variational Autoencoder Mixture Model
Sanduni Pinnawala, Annabelle Hartanto, Ivor J. A. Simpson, Peter A. Wijeratne
https://arxiv.org/abs/2509.15124

Learning Mechanistic Subtypes of Neurodegeneration with a Physics-Informed Variational Autoencoder Mixture Model
Modelling the underlying mechanisms of neurodegenerative diseases demands methods that capture heterogeneous and spatially varying dynamics from sparse, high-dimensional neuroimaging data. Integrating partial differential equation (PDE) based physics knowledge with machine learning provides enhanced interpretability and utility over classic numerical methods. However, current physics-integrated machine learning methods are limited to considering a single PDE, severely limiting their application…

RRRA: Resampling and Reranking through a Retriever Adapter
Bongsu Kim
https://arxiv.org/abs/2508.11670 https://arxiv.org/pdf/2508.11670

RRRA: Resampling and Reranking through a Retriever Adapter
In dense retrieval, effective training hinges on selecting high quality hard negatives while avoiding false negatives. Recent methods apply heuristics based on positive document scores to identify hard negatives, improving both performance and interpretability. However, these global, example agnostic strategies often miss instance specific false negatives. To address this, we propose a learnable adapter module that monitors Bi-Encoder representations to estimate the likelihood that a hard negat…

Deploying UDM Series in Real-Life Stuttered Speech Applications: A Clinical Evaluation Framework
Eric Zhang (SSHealth Team, AI for Healthcare Laboratory), Li Wei (SSHealth Team, AI for Healthcare Laboratory), Sarah Chen (SSHealth Team, AI for Healthcare Laboratory), Michael Wang (SSHealth Team, AI for Healthcare Laboratory)
https://arxiv.o…

Deploying UDM Series in Real-Life Stuttered Speech Applications: A Clinical Evaluation Framework
Stuttered and dysfluent speech detection systems have traditionally suffered from the trade-off between accuracy and clinical interpretability. While end-to-end deep learning models achieve high performance, their black-box nature limits clinical adoption. This paper looks at the Unconstrained Dysfluency Modeling (UDM) series-the current state-of-the-art framework developed by Berkeley that combines modular architecture, explicit phoneme alignment, and interpretable outputs for real-world clini…

KAN-HAR: A Human activity recognition based on Kolmogorov-Arnold Network
Mohammad Alikhani
https://arxiv.org/abs/2508.11186 https://arxiv.org/pdf/2508.1118…

KAN-HAR: A Human activity recognition based on Kolmogorov-Arnold Network
Human Activity Recognition (HAR) plays a critical role in numerous applications, including healthcare monitoring, fitness tracking, and smart environments. Traditional deep learning (DL) approaches, while effective, often require extensive parameter tuning and may lack interpretability. In this work, we investigate the use of a single three-axis accelerometer and the Kolmogorov--Arnold Network (KAN) for HAR tasks, leveraging its ability to model complex nonlinear relationships with improved int…

Rest2Visual: Predicting Visually Evoked fMRI from Resting-State Scans
Chuyang Zhou, Ziao Ji, Daochang Liu, Dongang Wang, Chenyu Wang, Chang Xu
https://arxiv.org/abs/2509.13612 h…

Rest2Visual: Predicting Visually Evoked fMRI from Resting-State Scans
Understanding how spontaneous brain activity relates to stimulus-driven neural responses is a fundamental challenge in cognitive neuroscience. While task-based functional magnetic resonance imaging (fMRI) captures localized stimulus-evoked brain activation, its acquisition is costly, time-consuming, and difficult to scale across populations. In contrast, resting-state fMRI (rs-fMRI) is task-free and abundant, but lacks direct interpretability. We introduce Rest2Visual, a conditional generative …

DF-LLaVA: Unlocking MLLM's potential for Synthetic Image Detection via Prompt-Guided Knowledge Injection
Zhuokang Shen, Kaisen Zhang, Bohan Jia, Yuan Fang, Zhou Yu, Shaohui Lin
https://arxiv.org/abs/2509.14957

DF-LLaVA: Unlocking MLLM's potential for Synthetic Image Detection via Prompt-Guided Knowledge Injection
With the increasing prevalence of synthetic images, evaluating image authenticity and locating forgeries accurately while maintaining human interpretability remains a challenging task. Existing detection models primarily focus on simple authenticity classification, ultimately providing only a forgery probability or binary judgment, which offers limited explanatory insights into image authenticity. Moreover, while MLLM-based detection methods can provide more interpretable results, they still la…

Floating-Body Hydrodynamic Neural Networks
Tianshuo Zhang, Wenzhe Zhai, Rui Yann, Jia Gao, He Cao, Xianglei Xing
https://arxiv.org/abs/2509.13783 https://a…

Floating-Body Hydrodynamic Neural Networks
Fluid-structure interaction is common in engineering and natural systems, where floating-body motion is governed by added mass, drag, and background flows. Modeling these dissipative dynamics is difficult: black-box neural models regress state derivatives with limited interpretability and unstable long-horizon predictions. We propose Floating-Body Hydrodynamic Neural Networks (FHNN), a physics-structured framework that predicts interpretable hydrodynamic parameters such as directional added mas…

From Sea to System: Exploring User-Centered Explainable AI for Maritime Decision Support
Doreen Jirak, Pieter Maes, Armeen Saroukanoff, Dirk van Rooy
https://arxiv.org/abs/2509.15084

From Sea to System: Exploring User-Centered Explainable AI for Maritime Decision Support
As autonomous technologies increasingly shape maritime operations, understanding why an AI system makes a decision becomes as crucial as what it decides. In complex and dynamic maritime environments, trust in AI depends not only on performance but also on transparency and interpretability. This paper highlights the importance of Explainable AI (XAI) as a foundation for effective human-machine teaming in the maritime domain, where informed oversight and shared understanding are essential. To sup…

Fairness-Aware and Interpretable Policy Learning
Nora Bearth, Michael Lechner, Jana Mareckova, Fabian Muny
https://arxiv.org/abs/2509.12119 https://arxiv.o…

Fairness-Aware and Interpretable Policy Learning
Fairness and interpretability play an important role in the adoption of decision-making algorithms across many application domains. These requirements are intended to avoid undesirable group differences and to alleviate concerns related to transparency. This paper proposes a framework that integrates fairness and interpretability into algorithmic decision making by combining data transformation with policy trees, a class of interpretable policy functions. The approach is based on pre-processing…

D4PM: A Dual-branch Driven Denoising Diffusion Probabilistic Model with Joint Posterior Diffusion Sampling for EEG Artifacts Removal
Feixue Shao, Xueyu Liu, Yongfei Wu, Jianbo Lu, Guiying Yan, Weihua Yang
https://arxiv.org/abs/2509.14302

D4PM: A Dual-branch Driven Denoising Diffusion Probabilistic Model with Joint Posterior Diffusion Sampling for EEG Artifacts Removal
Artifact removal is critical for accurate analysis and interpretation of Electroencephalogram (EEG) signals. Traditional methods perform poorly with strong artifact-EEG correlations or single-channel data. Recent advances in diffusion-based generative models have demonstrated strong potential for EEG denoising, notably improving fine-grained noise suppression and reducing over-smoothing. However, existing methods face two main limitations: lack of temporal modeling limits interpretability and t…

eDIF: A European Deep Inference Fabric for Remote Interpretability of LLM
Irma Heithoff. Marc Guggenberger, Sandra Kalogiannis, Susanne Mayer, Fabian Maag, Sigurd Schacht, Carsten Lanquillon
https://arxiv.org/abs/2508.10553

eDIF: A European Deep Inference Fabric for Remote Interpretability of LLM
This paper presents a feasibility study on the deployment of a European Deep Inference Fabric (eDIF), an NDIF-compatible infrastructure designed to support mechanistic interpretability research on large language models. The need for widespread accessibility of LLM interpretability infrastructure in Europe drives this initiative to democratize advanced model analysis capabilities for the research community. The project introduces a GPU-based cluster hosted at Ansbach University of Applied Scienc…

Checkmate: interpretable and explainable RSVQA is the endgame
Lucrezia Tosato, Christel Tartini Chappuis, Syrielle Montariol, Flora Weissgerber, Sylvain Lobry, Devis Tuia
https://arxiv.org/abs/2508.13086

Checkmate: interpretable and explainable RSVQA is the endgame
Remote Sensing Visual Question Answering (RSVQA) presents unique challenges in ensuring that model decisions are both understandable and grounded in visual content. Current models often suffer from a lack of interpretability and explainability, as well as from biases in dataset distributions that lead to shortcut learning. In this work, we tackle these issues by introducing a novel RSVQA dataset, Chessboard, designed to minimize biases through 3'123'253 questions and a balanced answer distribut…

RationAnomaly: Log Anomaly Detection with Rationality via Chain-of-Thought and Reinforcement Learning
Song Xu, Yilun Liu, Minggui He, Mingchen Dai, Ziang Chen, Chunguang Zhao, Jingzhou Du, Shimin Tao, Weibin Meng, Shenglin Zhang, Yongqian Sun, Boxing Chen, Daimeng Wei
https://arxiv.org/abs/2509.14693…

RationAnomaly: Log Anomaly Detection with Rationality via Chain-of-Thought and Reinforcement Learning
Logs constitute a form of evidence signaling the operational status of software systems. Automated log anomaly detection is crucial for ensuring the reliability of modern software systems. However, existing approaches face significant limitations: traditional deep learning models lack interpretability and generalization, while methods leveraging Large Language Models are often hindered by unreliability and factual inaccuracies. To address these issues, we propose RationAnomaly, a novel framewor…

Multi-Sensory Cognitive Computing for Learning Population-level Brain Connectivity
Mayssa Soussia, Mohamed Ali Mahjoub, Islem Rekik
https://arxiv.org/abs/2508.11436 https://

Multi-Sensory Cognitive Computing for Learning Population-level Brain Connectivity
The generation of connectional brain templates (CBTs) has recently garnered significant attention for its potential to identify unique connectivity patterns shared across individuals. However, existing methods for CBT learning such as conventional machine learning and graph neural networks (GNNs) are hindered by several limitations. These include: (i) poor interpretability due to their black-box nature, (ii) high computational cost, and (iii) an exclusive focus on structure and topology, overlo…

ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving
Jingyu Li, Bozhou Zhang, Xin Jin, Jiankang Deng, Xiatian Zhu, Li Zhang
https://arxiv.org/abs/2508.11428

ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving
Autonomous driving requires rich contextual comprehension and precise predictive reasoning to navigate dynamic and complex environments safely. Vision-Language Models (VLMs) and Driving World Models (DWMs) have independently emerged as powerful recipes addressing different aspects of this challenge. VLMs provide interpretability and robust action prediction through their ability to understand multi-modal context, while DWMs excel in generating detailed and plausible future driving scenarios ess…

From Distributional to Quantile Neural Basis Models: the case of Electricity Price Forecasting
Alessandro Brusaferri, Danial Ramin, Andrea Ballarino
https://arxiv.org/abs/2509.14113

From Distributional to Quantile Neural Basis Models: the case of Electricity Price Forecasting
While neural networks are achieving high predictive accuracy in multi-horizon probabilistic forecasting, understanding the underlying mechanisms that lead to feature-conditioned outputs remains a significant challenge for forecasters. In this work, we take a further step toward addressing this critical issue by introducing the Quantile Neural Basis Model, which incorporates the interpretability principles of Quantile Generalized Additive Models into an end-to-end neural network training framewo…

Trading-R1: Financial Trading with LLM Reasoning via Reinforcement Learning
Yijia Xiao, Edward Sun, Tong Chen, Fang Wu, Di Luo, Wei Wang
https://arxiv.org/abs/2509.11420 https:/…

Trading-R1: Financial Trading with LLM Reasoning via Reinforcement Learning
Developing professional, structured reasoning on par with human financial analysts and traders remains a central challenge in AI for finance, where markets demand interpretability and trust. Traditional time-series models lack explainability, while LLMs face challenges in turning natural-language analysis into disciplined, executable trades. Although reasoning LLMs have advanced in step-by-step planning and verification, their application to risk-sensitive financial decisions is underexplored. …

Deep Reinforcement Learning with Local Interpretability for Transparent Microgrid Resilience Energy Management
Mohammad Hossein Nejati Amiri, Fawaz Annaz, Mario De Oliveira, Florimond Gueniat
https://arxiv.org/abs/2508.08132

Deep Reinforcement Learning with Local Interpretability for Transparent Microgrid Resilience Energy Management
Renewable energy integration into microgrids has become a key approach to addressing global energy issues such as climate change and resource scarcity. However, the variability of renewable sources and the rising occurrence of High Impact Low Probability (HILP) events require innovative strategies for reliable and resilient energy management. This study introduces a practical approach to managing microgrid resilience through Explainable Deep Reinforcement Learning (XDRL). It combines the Proxim…

Residual MPC: Blending Reinforcement Learning with GPU-Parallelized Model Predictive Control
Se Hwan Jeon, Ho Jae Lee, Seungwoo Hong, Sangbae Kim
https://arxiv.org/abs/2510.12717

Residual MPC: Blending Reinforcement Learning with GPU-Parallelized Model Predictive Control
Model Predictive Control (MPC) provides interpretable, tunable locomotion controllers grounded in physical models, but its robustness depends on frequent replanning and is limited by model mismatch and real-time computational constraints. Reinforcement Learning (RL), by contrast, can produce highly robust behaviors through stochastic training but often lacks interpretability, suffers from out-of-distribution failures, and requires intensive reward engineering. This work presents a GPU-paralleli…

Crosslisted article(s) found for cs.HC. https://arxiv.org/list/cs.HC/new
[1/1]:
- User Perception of Attention Visualizations: Effects on Interpretability Across Evidence-Based Me...
Carvallo, Parra, Brusilovsky, Valdivieso, Rada, Donoso, Araujo

A Novel Study on Intelligent Methods and Explainable AI for Dynamic Malware Analysis
Richa Dasila, Vatsala Upadhyay, Samo Bobek, Abhishek Vaish
https://arxiv.org/abs/2508.10652 …

A Novel Study on Intelligent Methods and Explainable AI for Dynamic Malware Analysis
Deep learning models are one of the security strategies, trained on extensive datasets, and play a critical role in detecting and responding to these threats by recognizing complex patterns in malicious code. However, the opaque nature of these models-often described as "black boxes"-makes their decision-making processes difficult to understand, even for their creators. This research addresses these challenges by integrating Explainable AI (XAI) techniques to enhance the interpretability and tr…

Reinforcing Video Reasoning Segmentation to Think Before It Segments
Sitong Gong, Lu Zhang, Yunzhi Zhuge, Xu Jia, Pingping Zhang, Huchuan Lu
https://arxiv.org/abs/2508.11538 htt…

Reinforcing Video Reasoning Segmentation to Think Before It Segments
Video reasoning segmentation (VRS) endeavors to delineate referred objects in videos guided by implicit instructions that encapsulate human intent and temporal logic. Previous approaches leverage large vision language models (LVLMs) to encode object semantics into tokens for mask prediction. However, this paradigm suffers from limited interpretability during inference and suboptimal performance due to inadequate spatiotemporal reasoning. Drawing inspiration from seminal breakthroughs in r…

Graph Neural Diffusion via Generalized Opinion Dynamics
Asela Hevapathige, Asiri Wijesinghe, Ahad N. Zehmakan
https://arxiv.org/abs/2508.11249 https://arxi…

Graph Neural Diffusion via Generalized Opinion Dynamics
There has been a growing interest in developing diffusion-based Graph Neural Networks (GNNs), building on the connections between message passing mechanisms in GNNs and physical diffusion processes. However, existing methods suffer from three critical limitations: (1) they rely on homogeneous diffusion with static dynamics, limiting adaptability to diverse graph structures; (2) their depth is constrained by computational overhead and diminishing interpretability; and (3) theoretical understandi…

Structured Kernel Regression VAE: A Computationally Efficient Surrogate for GP-VAEs in ICA
Yuan-Hao Wei, Fu-Hao Deng, Lin-Yong Cui, Yan-Jie Sun
https://arxiv.org/abs/2508.09721 …

Structured Kernel Regression VAE: A Computationally Efficient Surrogate for GP-VAEs in ICA
The interpretability of generative models is considered a key factor in demonstrating their effectiveness and controllability. The generated data are believed to be determined by latent variables that are not directly observable. Therefore, disentangling, decoupling, decomposing, causal inference, or performing Independent Component Analysis (ICA) in the latent variable space helps uncover the independent factors that influence the attributes or features affecting the generated outputs, thereby…

Genome-Factory: An Integrated Library for Tuning, Deploying, and Interpreting Genomic Models
Weimin Wu, Xuefeng Song, Yibo Wen, Qinjie Lin, Zhihan Zhou, Jerry Yao-Chieh Hu, Zhong Wang, Han Liu
https://arxiv.org/abs/2509.12266

Genome-Factory: An Integrated Library for Tuning, Deploying, and Interpreting Genomic Models
We introduce Genome-Factory, an integrated Python library for tuning, deploying, and interpreting genomic models. Our core contribution is to simplify and unify the workflow for genomic model development: data collection, model tuning, inference, benchmarking, and interpretability. For data collection, Genome-Factory offers an automated pipeline to download genomic sequences and preprocess them. It also includes quality control, such as GC content normalization. For model tuning, Genome-Factory…

Mechanistic Interpretability of Code Correctness in LLMs via Sparse Autoencoders
Kriz Tahimic, Charibeth Cheng
https://arxiv.org/abs/2510.02917 https://arx…

Mechanistic Interpretability of Code Correctness in LLMs via Sparse Autoencoders
As Large Language Models become integral to software development, with substantial portions of AI-suggested code entering production, understanding their internal correctness mechanisms becomes critical for safe deployment. We apply sparse autoencoders to decompose LLM representations, identifying directions that correspond to code correctness. We select predictor directions using t-statistics and steering directions through separation scores from base model representations, then analyze their …

Crosslisted article(s) found for q-fin.RM. https://arxiv.org/list/q-fin.RM/new
[1/1]:
- Enhancing ML Models Interpretability for Credit Scoring
Sagi Schwartz, Qinling Wang, Fang Fang
…

Behind the Scenes: Mechanistic Interpretability of LoRA-adapted Whisper for Speech Emotion Recognition
Yujian Ma, Jinqiu Sang, Ruizhe Li
https://arxiv.org/abs/2509.08454 https:/…

Behind the Scenes: Mechanistic Interpretability of LoRA-adapted Whisper for Speech Emotion Recognition
Large pre-trained speech models such as Whisper offer strong generalization but pose significant challenges for resource-efficient adaptation. Low-Rank Adaptation (LoRA) has become a popular parameter-efficient fine-tuning method, yet its underlying mechanisms in speech tasks remain poorly understood. In this work, we conduct the first systematic mechanistic interpretability study of LoRA within the Whisper encoder for speech emotion recognition (SER). Using a suite of analytical tools, includi…

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability
Bianca Raimondi, Daniela Dalbagno, Maurizio Gabbrielli
https://arxiv.org/abs/2510.12229 https://

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability
Large language models (LLMs) have been shown to internalize human-like biases during finetuning, yet the mechanisms by which these biases manifest remain unclear. In this work, we investigated whether the well-known Knobe effect, a moral bias in intentionality judgements, emerges in finetuned LLMs and whether it can be traced back to specific components of the model. We conducted a Layer-Patching analysis across 3 open-weights LLMs and demonstrated that the bias is not only learned during finet…

Targeted Sequential Pattern Mining with High Average Utility
Kai Cao, Yucong Duan, Wensheng Gan
https://arxiv.org/abs/2510.10115 https://arxiv.org/pdf/2510…

Targeted Sequential Pattern Mining with High Average Utility
Incorporating utility into targeted pattern mining can address the practical limitations of traditional frequency-based approaches. However, utility-based methods often suffer from generating a large number of long and complicated sequences. To improve pattern relevance and interpretability, average utility provides a more balanced metric by considering both utility and sequence length. Moreover, incorporating user-defined query targets into the mining process enhances usability and interactivi…

Dynamic Local Average Treatment Effects in Time Series
Alessandro Casini, Adam McCloskey, Luca Rolla, Raimondo Pala
https://arxiv.org/abs/2509.12985 https://

Dynamic Local Average Treatment Effects in Time Series
This paper discusses identification, estimation, and inference on dynamic local average treatment effects (LATEs) in instrumental variables (IVs) settings. First, we show that compliers--observations whose treatment status is affected by the instrument--can be identified individually in time series data using smoothness assumptions and local comparisons of treatment assignments. Second, we show that this result enables not only better interpretability of IV estimates but also direct testing of …

CLAIRE: A Dual Encoder Network with RIFT Loss and Phi-3 Small Language Model Based Interpretability for Cross-Modality Synthetic Aperture Radar and Optical Land Cover Segmentation
Debopom Sutradhar, Arefin Ittesafun Abian, Mohaimenul Azam Khan Raiaan, Reem E. Mohamed, Sheikh Izzal Azid, Sami Azam
https://arxiv.org/abs/2509.11952

CLAIRE: A Dual Encoder Network with RIFT Loss and Phi-3 Small Language Model Based Interpretability for Cross-Modality Synthetic Aperture Radar and Optical Land Cover Segmentation
Accurate land cover classification from satellite imagery is crucial in environmental monitoring and sustainable resource management. However, it remains challenging due to the complexity of natural landscapes, the visual similarity between classes, and the significant class imbalance in the available datasets. To address these issues, we propose a dual encoder architecture that independently extracts modality-specific features from optical and Synthetic Aperture Radar (SAR) imagery, which are …

Sparse-Group Factor Analysis for High-Dimensional Time Series
Xin Wang, Xialu Liu
https://arxiv.org/abs/2510.05370 https://arxiv.org/pdf/2510.05370

Sparse-Group Factor Analysis for High-Dimensional Time Series
Factor analysis is a widely used technique for dimension reduction in high-dimensional data. However, a key challenge in factor models lies in the interpretability of the latent factors. One intuitive way to interpret these factors is through their associated loadings. Liu and Wang proposed a novel framework that redefines factor models with sparse loadings to enhance interpretability. In many high-dimensional time series applications, variables exhibit natural group structures. Building on thi…

A Triad of Networks and a Triad of Fusions for the Other Climate Crisis
Emilio Porcu, Tobia Filosi, Horst Simon
https://arxiv.org/abs/2510.09728 https://ar…

A Triad of Networks and a Triad of Fusions for the Other Climate Crisis
Shaw and Stevens call for a new paradigm in climate science criticizes Large Scale Determinism in favor of (i) embracing discrepancies, (ii) embracing hierarchies, and (iii) create disruption while keeping interpretability. The last 20 years have seen a plethora of contributions relating complex networks with climate data and climate models. We provide a view of climate networks through a triad of frameworks and associated paradigms: (a) networks of data, where both (geographical) nodes and the…

Do Natural Language Descriptions of Model Activations Convey Privileged Information?
Millicent Li, Alberto Mario Ceballos Arroyo, Giordano Rogers, Naomi Saphra, Byron C. Wallace
https://arxiv.org/abs/2509.13316

Do Natural Language Descriptions of Model Activations Convey Privileged Information?
Recent interpretability methods have proposed to translate LLM internal representations into natural language descriptions using a second verbalizer LLM. This is intended to illuminate how the target model represents and operates on inputs. But do such activation verbalization approaches actually provide privileged knowledge about the internal workings of the target model, or do they merely convey information about its inputs? We critically evaluate popular verbalization methods across datasets…

Approximate combinatorial optimization with Rydberg atoms: the barrier of interpretability
Christian de Correc, Thomas Ayral, Corentin Bertrand
https://arxiv.org/abs/2507.22761 …

Approximate combinatorial optimization with Rydberg atoms: the barrier of interpretability
Analog quantum computing with Rydberg atoms is seen as an avenue to solve hard graph optimization problems, because they naturally encode the Maximum Independent Set (MIS) problem on Unit-Disk (UD) graphs, a problem that admits rather efficient approximation schemes on classical computers. Going beyond UD-MIS to address generic graphs requires embedding schemes, typically with chains of ancilla atoms, and an interpretation algorithm to map results back to the original problem. However, interpre…

Algorithmic Tradeoffs, Applied NLP, and the State-of-the-Art Fallacy
AJ Alvero, Ruohong Dong, Klint Kanopka, David Lang
https://arxiv.org/abs/2509.08199 https://

Algorithmic Tradeoffs, Applied NLP, and the State-of-the-Art Fallacy
Computational sociology is growing in popularity, yet the analytic tools employed differ widely in power, transparency, and interpretability. In computer science, methods gain popularity after surpassing benchmarks of predictive accuracy, becoming the "state of the art." Computer scientists favor novelty and innovation for different reasons, but prioritizing technical prestige over methodological fit could unintentionally limit the scope of sociological inquiry. To illustrate, we focus on compu…

Interpretability as Alignment: Making Internal Understanding a Design Principle
Aadit Sengupta, Pratinav Seth, Vinay Kumar Sankarapu
https://arxiv.org/abs/2509.08592 https://

Interpretability as Alignment: Making Internal Understanding a Design Principle
Large neural models are increasingly deployed in high-stakes settings, raising concerns about whether their behavior reliably aligns with human values. Interpretability provides a route to internal transparency by revealing the computations that drive outputs. We argue that interpretability especially mechanistic approaches should be treated as a design principle for alignment, not an auxiliary diagnostic tool. Post-hoc methods such as LIME or SHAP offer intuitive but correlational explanations…

Model-agnostic post-hoc explainability for recommender systems
Irina Ar\'evalo, Jose L Salmeron
https://arxiv.org/abs/2509.10245 https://arxiv.org/pdf/…

Model-agnostic post-hoc explainability for recommender systems
Recommender systems often benefit from complex feature embeddings and deep learning algorithms, which deliver sophisticated recommendations that enhance user experience, engagement, and revenue. However, these methods frequently reduce the interpretability and transparency of the system. In this research, we develop a systematic application, adaptation, and evaluation of deletion diagnostics in the recommender setting. The method compares the performance of a model to that of a similar model tr…

DeGuV: Depth-Guided Visual Reinforcement Learning for Generalization and Interpretability in Manipulation
Tien Pham, Xinyun Chi, Khang Nguyen, Manfred Huber, Angelo Cangelosi
https://arxiv.org/abs/2509.04970

DeGuV: Depth-Guided Visual Reinforcement Learning for Generalization and Interpretability in Manipulation
Reinforcement learning (RL) agents can learn to solve complex tasks from visual inputs, but generalizing these learned skills to new environments remains a major challenge in RL application, especially robotics. While data augmentation can improve generalization, it often compromises sample efficiency and training stability. This paper introduces DeGuV, an RL framework that enhances both generalization and sample efficiency. In specific, we leverage a learnable masker network that produces a ma…

FireGNN: Neuro-Symbolic Graph Neural Networks with Trainable Fuzzy Rules for Interpretable Medical Image Classification
Prajit Sengupta, Islem Rekik
https://arxiv.org/abs/2509.10510

FireGNN: Neuro-Symbolic Graph Neural Networks with Trainable Fuzzy Rules for Interpretable Medical Image Classification
Medical image classification requires not only high predictive performance but also interpretability to ensure clinical trust and adoption. Graph Neural Networks (GNNs) offer a powerful framework for modeling relational structures within datasets; however, standard GNNs often operate as black boxes, limiting transparency and usability, particularly in clinical settings. In this work, we present an interpretable graph-based learning framework named FireGNN that integrates trainable fuzzy rules i…

Rethinking Human Preference Evaluation of LLM Rationales
Ziang Li, Manasi Ganti, Zixian Ma, Helena Vasconcelos, Qijia He, Ranjay Krishna
https://arxiv.org/abs/2509.11026 https:/…

Rethinking Human Preference Evaluation of LLM Rationales
Large language models (LLMs) often generate natural language rationales -- free-form explanations that help improve performance on complex reasoning tasks and enhance interpretability for human users. However, evaluating these rationales remains challenging. While recent work has relied on binary preference judgments from humans or LLM judges, such evaluations are often opaque and coarse-grained, offering limited insight into what makes one rationale better than another. In this work, we rethin…

Explainable Ensemble Learning for Graph-Based Malware Detection
Hossein Shokouhinejad, Roozbeh Razavi-Far, Griffin Higgins, Ali A Ghorbani
https://arxiv.org/abs/2508.09801 https…

Explainable Ensemble Learning for Graph-Based Malware Detection
Malware detection in modern computing environments demands models that are not only accurate but also interpretable and robust to evasive techniques. Graph neural networks (GNNs) have shown promise in this domain by modeling rich structural dependencies in graph-based program representations such as control flow graphs (CFGs). However, single-model approaches may suffer from limited generalization and lack interpretability, especially in high-stakes security applications. In this paper, we prop…

Reduction of motion artifacts from photoplethysmography signals using learned convolutional sparse coding
Giulio Basso, Xi Long, Reinder Haakma, Rik Vullings
https://arxiv.org/abs/2508.10805

Reduction of motion artifacts from photoplethysmography signals using learned convolutional sparse coding
Objective. Wearable devices with embedded photoplethysmography (PPG) enable continuous non-invasive monitoring of cardiac activity, offering a promising strategy to reduce the global burden of cardiovascular diseases. However, monitoring during daily life introduces motion artifacts that can compromise the signals. Traditional signal decomposition techniques often fail with severe artifacts. Deep learning denoisers are more effective but have poorer interpretability, which is critical for clini…

Hierarchical Variable Importance with Statistical Control for Medical Data-Based Prediction
Joseph Paillard, Antoine Collas, Denis A. Engemann, Bertrand Thirion
https://arxiv.org/abs/2508.08724

Hierarchical Variable Importance with Statistical Control for Medical Data-Based Prediction
Recent advances in machine learning have greatly expanded the repertoire of predictive methods for medical imaging. However, the interpretability of complex models remains a challenge, which limits their utility in medical applications. Recently, model-agnostic methods have been proposed to measure conditional variable importance and accommodate complex non-linear models. However, they often lack power when dealing with highly correlated data, a common problem in medical imaging. We introduce H…

Co-Authoring the Self: A Human-AI Interface for Interest Reflection in Recommenders
Ruixuan Sun, Junyuan Wang, Sanjali Roy, Joseph A. Konstan
https://arxiv.org/abs/2510.08930 ht…

Co-Authoring the Self: A Human-AI Interface for Interest Reflection in Recommenders
Natural language-based user profiles in recommender systems have been explored for their interpretability and potential to help users scrutinize and refine their interests, thereby improving recommendation quality. Building on this foundation, we introduce a human-AI collaborative profile for a movie recommender system that presents editable personalized interest summaries of a user's movie history. Unlike static profiles, this design invites users to directly inspect, modify, and reflect on th…

Think as a Doctor: An Interpretable AI Approach for ICU Mortality Prediction
Qingwen Li, Xiaohang Zhao, Xiao Han, Hailiang Huang, Lanjuan Liu
https://arxiv.org/abs/2510.11745 ht…

Think as a Doctor: An Interpretable AI Approach for ICU Mortality Prediction
Intensive Care Unit (ICU) mortality prediction, which estimates a patient's mortality status at discharge using EHRs collected early in an ICU admission, is vital in critical care. For this task, predictive accuracy alone is insufficient; interpretability is equally essential for building clinical trust and meeting regulatory standards, a topic that has attracted significant attention in information system research. Accordingly, an ideal solution should enable intrinsic interpretability and ali…

Why Bonds Fail Differently? Explainable Multimodal Learning for Multi-Class Default Prediction
Yi Lu, Aifan Ling, Chaoqun Wang, Yaxin Xu
https://arxiv.org/abs/2509.10802 https:/…

Why Bonds Fail Differently? Explainable Multimodal Learning for Multi-Class Default Prediction
In recent years, China's bond market has seen a surge in defaults amid regulatory reforms and macroeconomic volatility. Traditional machine learning models struggle to capture financial data's irregularity and temporal dependencies, while most deep learning models lack interpretability-critical for financial decision-making. To tackle these issues, we propose EMDLOT (Explainable Multimodal Deep Learning for Time-series), a novel framework for multi-class bond default prediction. EMDLOT integrat…

How to Evaluate Medical AI
Ilia Kopanichuk, Petr Anokhin, Vladimir Shaposhnikov, Vladimir Makharev, Ekaterina Tsapieva, Iaroslav Bespalov, Dmitry V. Dylov, Ivan Oseledets
https://arxiv.org/abs/2509.11941

How to Evaluate Medical AI
The integration of artificial intelligence (AI) into medical diagnostic workflows requires robust and consistent evaluation methods to ensure reliability, clinical relevance, and the inherent variability in expert judgments. Traditional metrics like precision and recall often fail to account for the inherent variability in expert judgments, leading to inconsistent assessments of AI performance. Inter-rater agreement statistics like Cohen's Kappa are more reliable but they lack interpretability.…

Crosslisted article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new
[1/1]:
- User Perception of Attention Visualizations: Effects on Interpretability Across Evidence-Based Me...
Carvallo, Parra, Brusilovsky, Valdivieso, Rada, Donoso, Araujo

Protocode: Prototype-Driven Interpretability for Code Generation in LLMs
Krishna Vamshi Bodla, Haizhao Yang
https://arxiv.org/abs/2509.25247 https://arxiv.…

Protocode: Prototype-Driven Interpretability for Code Generation in LLMs
Since the introduction of Large Language Models (LLMs), they have been widely adopted for various tasks such as text summarization, question answering, speech-to-text translation, and more. In recent times, the use of LLMs for code generation has gained significant attention, with tools such as Cursor and Windsurf demonstrating the ability to analyze massive code repositories and recommend relevant changes. Big tech companies have also acknowledged the growing reliance on LLMs for code generati…

Repulsive Mixture Model with Projection Determinantal Point Process
Ziyi Song, Federico Camerlenghi, Weining Shen, Michele Guindani, Mario Beraha
https://arxiv.org/abs/2510.08838

Repulsive Mixture Model with Projection Determinantal Point Process
In many scientific domains, clustering aims to reveal interpretable latent structure that reflects relevant subpopulations or processes. Widely used Bayesian mixture models for model-based clustering often produce overlapping or redundant components because priors on cluster locations are specified independently, hindering interpretability. To mitigate this, repulsive priors have been proposed to encourage well-separated components, yet existing approaches face both computational and theoretica…

SCDTour: Embedding Axis Ordering and Merging for Interpretable Semantic Change Detection
Taichi Aida, Danushka Bollegala
https://arxiv.org/abs/2509.11818 https://

SCDTour: Embedding Axis Ordering and Merging for Interpretable Semantic Change Detection
In Semantic Change Detection (SCD), it is a common problem to obtain embeddings that are both interpretable and high-performing. However, improving interpretability often leads to a loss in the SCD performance, and vice versa. To address this problem, we propose SCDTour, a method that orders and merges interpretable axes to alleviate the performance degradation of SCD. SCDTour considers both (a) semantic similarity between axes in the embedding space, as well as (b) the degree to which each axi…

Causality and Interpretability for Electrical Distribution System faults
Karthik Peddi, Sai Ram Aditya Parisineni, Hemanth Macharla, Mayukha Pal
https://arxiv.org/abs/2508.02524

Causality and Interpretability for Electrical Distribution System faults
Causal analysis helps us understand variables that are responsible for system failures. This improves fault detection and makes system more reliable. In this work, we present a new method that combines causal inference with machine learning to classify faults in electrical distribution systems (EDS) using graph-based models. We first build causal graphs using transfer entropy (TE). Each fault case is represented as a graph, where the nodes are features such as voltage and current, and the edges…

Audio-Maestro: Enhancing Large Audio-Language Models with Tool-Augmented Reasoning
Kuan-Yi Lee, Tsung-En Lin, Hung-Yi Lee
https://arxiv.org/abs/2510.11454 https://

Audio-Maestro: Enhancing Large Audio-Language Models with Tool-Augmented Reasoning
Recent advancements in large multimodal models (LMMs) have shown strong capabilities in audio understanding. However, most systems rely solely on end-to-end reasoning, limiting interpretability and accuracy for tasks that require structured knowledge or specialized signal analysis. In this work, we present Audio-Maestro -- a tool-augmented audio reasoning framework that enables audio-language models to autonomously call external tools and integrate their timestamped outputs into the reasoning p…

Foundational theory for optimal decision tree problems. II. Optimal hypersurface decision tree algorithm
Xi He
https://arxiv.org/abs/2509.12057 https://arx…

Foundational theory for optimal decision tree problems. II. Optimal hypersurface decision tree algorithm
Decision trees are a ubiquitous model for classification and regression tasks due to their interpretability and efficiency. However, solving the optimal decision tree (ODT) problem remains a challenging combinatorial optimization task. Even for the simplest splitting rules--axis-parallel hyperplanes--it is NP-hard to optimize. In Part I of this series, we rigorously defined the proper decision tree model through four axioms and, based on these, introduced four formal definitions of the ODT prob…

Empowering LLM Agents with Geospatial Awareness: Toward Grounded Reasoning for Wildfire Response
Yiheng Chen, Lingyao Li, Zihui Ma, Qikai Hu, Yilun Zhu, Min Deng, Runlong Yu
https://arxiv.org/abs/2510.12061

Empowering LLM Agents with Geospatial Awareness: Toward Grounded Reasoning for Wildfire Response
Effective disaster response is essential for safeguarding lives and property. Existing statistical approaches often lack semantic context, generalize poorly across events, and offer limited interpretability. While Large language models (LLMs) provide few-shot generalization, they remain text-bound and blind to geography. To bridge this gap, we introduce a Geospatial Awareness Layer (GAL) that grounds LLM agents in structured earth data. Starting from raw wildfire detections, GAL automatically r…

Enhancing Interpretability and Effectiveness in Recommendation with Numerical Features via Learning to Contrast the Counterfactual samples
Xiaoxiao Xu, Hao Wu, Wenhui Yu, Lantao Hu, Peng Jiang, Kun Gai
https://arxiv.org/abs/2509.03187

Enhancing Interpretability and Effectiveness in Recommendation with Numerical Features via Learning to Contrast the Counterfactual samples
We propose a general model-agnostic Contrastive learning framework with Counterfactual Samples Synthesizing (CCSS) for modeling the monotonicity between the neural network output and numerical features which is critical for interpretability and effectiveness of recommender systems. CCSS models the monotonicity via a two-stage process: synthesizing counterfactual samples and contrasting the counterfactual samples. The two techniques are naturally integrated into a model-agnostic framework, formi…

Risk Map As Middleware: Towards Interpretable Cooperative End-to-end Autonomous Driving for Risk-Aware Planning
Mingyue Lei, Zewei Zhou, Hongchen Li, Jiaqi Ma, Jia Hu
https://arxiv.org/abs/2508.07686

Risk Map As Middleware: Towards Interpretable Cooperative End-to-end Autonomous Driving for Risk-Aware Planning
End-to-end paradigm has emerged as a promising approach to autonomous driving. However, existing single-agent end-to-end pipelines are often constrained by occlusion and limited perception range, resulting in hazardous driving. Furthermore, their black-box nature prevents the interpretability of the driving behavior, leading to an untrustworthiness system. To address these limitations, we introduce Risk Map as Middleware (RiskMM) and propose an interpretable cooperative end-to-end driving frame…

Hybrid Explanation-Guided Learning for Transformer-Based Chest X-Ray Diagnosis
Shelley Zixin Shu, Haozhe Luo, Alexander Poellinger, Mauricio Reyes
https://arxiv.org/abs/2510.12704

Hybrid Explanation-Guided Learning for Transformer-Based Chest X-Ray Diagnosis
Transformer-based deep learning models have demonstrated exceptional performance in medical imaging by leveraging attention mechanisms for feature representation and interpretability. However, these models are prone to learning spurious correlations, leading to biases and limited generalization. While human-AI attention alignment can mitigate these issues, it often depends on costly manual supervision. In this work, we propose a Hybrid Explanation-Guided Learning (H-EGL) framework that combines…

Extending the Entropic Potential of Events for Uncertainty Quantification and Decision-Making in Artificial Intelligence
Mark Zilberman
https://arxiv.org/abs/2508.10241 https://…

Extending the Entropic Potential of Events for Uncertainty Quantification and Decision-Making in Artificial Intelligence
This work demonstrates how the concept of the entropic potential of events -- a parameter quantifying the influence of discrete events on the expected future entropy of a system -- can enhance uncertainty quantification, decision-making, and interpretability in artificial intelligence (AI). Building on its original formulation in physics, the framework is adapted for AI by introducing an event-centric measure that captures how actions, observations, or other discrete occurrences impact uncertai…

Quantifying the Accuracy-Interpretability Trade-Off in Concept-Based Sidechannel Models
David Debot, Giuseppe Marra
https://arxiv.org/abs/2510.05670 https://

Quantifying the Accuracy-Interpretability Trade-Off in Concept-Based Sidechannel Models
Concept Bottleneck Models (CBNMs) are deep learning models that provide interpretability by enforcing a bottleneck layer where predictions are based exclusively on human-understandable concepts. However, this constraint also restricts information flow and often results in reduced predictive accuracy. Concept Sidechannel Models (CSMs) address this limitation by introducing a sidechannel that bypasses the bottleneck and carry additional task-relevant information. While this improves accuracy, it …

Denoised IPW-Lasso for Heterogeneous Treatment Effect Estimation in Randomized Experiments
Mingqian Guan, Komei Fujita, Naoya Sueishi, Shota Yasui
https://arxiv.org/abs/2510.10527

Denoised IPW-Lasso for Heterogeneous Treatment Effect Estimation in Randomized Experiments
This paper proposes a new method for estimating conditional average treatment effects (CATE) in randomized experiments. We adopt inverse probability weighting (IPW) for identification; however, IPW-transformed outcomes are known to be noisy, even when true propensity scores are used. To address this issue, we introduce a noise reduction procedure and estimate a linear CATE model using Lasso, achieving both accuracy and interpretability. We theoretically show that denoising reduces the predictio…

Sparse Deep Additive Model with Interactions: Enhancing Interpretability and Predictability
Yi-Ting Hung, Li-Hsiang Lin, Vince D. Calhoun
https://arxiv.org/abs/2509.23068 https:…

Sparse Deep Additive Model with Interactions: Enhancing Interpretability and Predictability
Recent advances in deep learning highlight the need for personalized models that can learn from small or moderate samples, handle high dimensional features, and remain interpretable. To address this challenge, we propose the Sparse Deep Additive Model with Interactions (SDAMI), a framework that combines sparsity driven feature selection with deep subnetworks for flexible function approximation. Unlike conventional deep learning models, which often function as black boxes, SDAMI explicitly disen…

Towards Reliable and Interpretable Document Question Answering via VLMs
Alessio Chen, Simone Giovannini, Andrea Gemelli, Fabio Coppini, Simone Marinai
https://arxiv.org/abs/2509.10129

Towards Reliable and Interpretable Document Question Answering via VLMs
Vision-Language Models (VLMs) have shown strong capabilities in document understanding, particularly in identifying and extracting textual information from complex documents. Despite this, accurately localizing answers within documents remains a major challenge, limiting both interpretability and real-world applicability. To address this, we introduce \textit{DocExplainerV0}, a plug-and-play bounding-box prediction module that decouples answer generation from spatial localization. This design m…

LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Real-World Multilingual VQA
Jing Huang, Zhiya Tan, Shutao Gong, Fanwei Zeng, Jianshu Li
https://arxiv.org/abs/2509.10026

LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Real-World Multilingual VQA
As large vision language models (VLMs) advance, their capabilities in multilingual visual question answering (mVQA) have significantly improved. Chain-of-thought (CoT) reasoning has been proven to enhance interpretability and complex reasoning. However, most existing approaches rely primarily on textual CoT and provide limited support for multilingual multimodal reasoning, constraining their deployment in real-world applications. To address this gap, we introduce \textbf{LaV-CoT}, the first Lan…

HiCoTraj:Zero-Shot Demographic Reasoning via Hierarchical Chain-of-Thought Prompting from Trajectory
Junyi Xie, Yuankun Jiao, Jina Kim, Yao-Yi Chiang, Lingyi Zhao, Khurram Shafique
https://arxiv.org/abs/2510.12067

HiCoTraj:Zero-Shot Demographic Reasoning via Hierarchical Chain-of-Thought Prompting from Trajectory
Inferring demographic attributes such as age, sex, or income level from human mobility patterns enables critical applications such as targeted public health interventions, equitable urban planning, and personalized transportation services. Existing mobility-based demographic inference studies heavily rely on large-scale trajectory data with demographic labels, leading to limited interpretability and poor generalizability across different datasets and user groups. We propose HiCoTraj (Zero-Shot …

Beyond Transcription: Mechanistic Interpretability in ASR
Neta Glazer, Yael Segal-Feldman, Hilit Segev, Aviv Shamsian, Asaf Buchnick, Gill Hetz, Ethan Fetaya, Joseph Keshet, Aviv Navon
https://arxiv.org/abs/2508.15882

Beyond Transcription: Mechanistic Interpretability in ASR
Interpretability methods have recently gained significant attention, particularly in the context of large language models, enabling insights into linguistic representations, error detection, and model behaviors such as hallucinations and repetitions. However, these techniques remain underexplored in automatic speech recognition (ASR), despite their potential to advance both the performance and interpretability of ASR systems. In this work, we adapt and systematically apply established interpret…

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation
Huizhen Shu, Xuying Li, Qirui Wang, Yuji Kosuga, Mengqiu Tian, Zhuo Li
https://arxiv.org/abs/2508.10404

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation
With the rapid proliferation of Natural Language Processing (NLP), especially Large Language Models (LLMs), generating adversarial examples to jailbreak LLMs remains a key challenge for understanding model vulnerabilities and improving robustness. In this context, we propose a new black-box attack method that leverages the interpretability of large models. We introduce the Sparse Feature Perturbation Framework (SFPF), a novel approach for adversarial text generation that utilizes sparse autoenc…

Situationally-aware Path Planning Exploiting 3D Scene Graphs
Saad Ejaz, Marco Giberna, Muhammad Shaheer, Jose Andres Millan-Romera, Ali Tourani, Paul Kremer, Holger Voos, Jose Luis Sanchez-Lopez
https://arxiv.org/abs/2508.06283

Situationally-aware Path Planning Exploiting 3D Scene Graphs
3D Scene Graphs integrate both metric and semantic information, yet their structure remains underutilized for improving path planning efficiency and interpretability. In this work, we present S-Path, a situationally-aware path planner that leverages the metric-semantic structure of indoor 3D Scene Graphs to significantly enhance planning efficiency. S-Path follows a two-stage process: it first performs a search over a semantic graph derived from the scene graph to yield a human-understandable h…

Exploring Expert Specialization through Unsupervised Training in Sparse Mixture of Experts
Strahinja Nikolic, Ilker Oguz, Demetri Psaltis
https://arxiv.org/abs/2509.10025 https:…

Exploring Expert Specialization through Unsupervised Training in Sparse Mixture of Experts
Understanding the internal organization of neural networks remains a fundamental challenge in deep learning interpretability. We address this challenge by exploring a novel Sparse Mixture of Experts Variational Autoencoder (SMoE-VAE) architecture. We test our model on the QuickDraw dataset, comparing unsupervised expert routing against a supervised baseline guided by ground-truth labels. Surprisingly, we find that unsupervised routing consistently achieves superior reconstruction performance. T…

From <Answer> to <Think>: Multidimensional Supervision of Reasoning Process for LLM Optimization
Beining Wang, Weihang Su, Hongtao Tian, Tao Yang, Yujia Zhou, Ting Yao, Qingyao Ai, Yiqun Liu
https://arxiv.org/abs/2510.11457

From to : Multidimensional Supervision of Reasoning Process for LLM Optimization
Improving the multi-step reasoning ability of Large Language Models (LLMs) is a critical yet challenging task. The dominant paradigm, outcome-supervised reinforcement learning (RLVR), rewards only correct final answers, often propagating flawed reasoning and suffering from sparse reward signals. While process-level reward models (PRMs) provide denser, step-by-step feedback, they lack generalizability and interpretability, requiring task-specific segmentation of the reasoning process. To this en…

LIA-X: Interpretable Latent Portrait Animator
Yaohui Wang, Di Yang, Xinyuan Chen, Francois Bremond, Yu Qiao, Antitza Dantcheva
https://arxiv.org/abs/2508.09959 https://

LIA-X: Interpretable Latent Portrait Animator
We introduce LIA-X, a novel interpretable portrait animator designed to transfer facial dynamics from a driving video to a source portrait with fine-grained control. LIA-X is an autoencoder that models motion transfer as a linear navigation of motion codes in latent space. Crucially, it incorporates a novel Sparse Motion Dictionary that enables the model to disentangle facial dynamics into interpretable factors. Deviating from previous 'warp-render' approaches, the interpretability of the Spars…

The Loss Kernel: A Geometric Probe for Deep Learning Interpretability
Maxwell Adam, Zach Furman, Jesse Hoogland
https://arxiv.org/abs/2509.26537 https://ar…

The Loss Kernel: A Geometric Probe for Deep Learning Interpretability
We introduce the loss kernel, an interpretability method for measuring similarity between data points according to a trained neural network. The kernel is the covariance matrix of per-sample losses computed under a distribution of low-loss-preserving parameter perturbations. We first validate our method on a synthetic multitask problem, showing it separates inputs by task as predicted by theory. We then apply this kernel to Inception-v1 to visualize the structure of ImageNet, and we show that t…

Towards Perfection: Building Inter-component Mutual Correction for Retinex-based Low-light Image Enhancement
Luyang Cao, Han Xu, Jian Zhang, Lei Qi, Jiayi Ma, Yinghuan Shi, Yang Gao
https://arxiv.org/abs/2508.09009

Towards Perfection: Building Inter-component Mutual Correction for Retinex-based Low-light Image Enhancement
In low-light image enhancement, Retinex-based deep learning methods have garnered significant attention due to their exceptional interpretability. These methods decompose images into mutually independent illumination and reflectance components, allows each component to be enhanced separately. In fact, achieving perfect decomposition of illumination and reflectance components proves to be quite challenging, with some residuals still existing after decomposition. In this paper, we formally name t…

RADAR: Mechanistic Pathways for Detecting Data Contamination in LLM Evaluation
Ashish Kattamuri, Harshwardhan Fartale, Arpita Vats, Rahul Raja, Ishita Prasad
https://arxiv.org/abs/2510.08931

RADAR: Mechanistic Pathways for Detecting Data Contamination in LLM Evaluation
Data contamination poses a significant challenge to reliable LLM evaluation, where models may achieve high performance by memorizing training data rather than demonstrating genuine reasoning capabilities. We introduce RADAR (Recall vs. Reasoning Detection through Activation Representation), a novel framework that leverages mechanistic interpretability to detect contamination by distinguishing recall-based from reasoning-based model responses. RADAR extracts 37 features spanning surface-level co…

Prime Implicant Explanations for Reaction Feasibility Prediction
Klaus Weinbauer, Tieu-Long Phan, Peter F. Stadler, Thomas G\"artner, Sagar Malhotra
https://arxiv.org/abs/2510.09226

Prime Implicant Explanations for Reaction Feasibility Prediction
Machine learning models that predict the feasibility of chemical reactions have become central to automated synthesis planning. Despite their predictive success, these models often lack transparency and interpretability. We introduce a novel formulation of prime implicant explanations--also known as minimally sufficient reasons--tailored to this domain, and propose an algorithm for computing such explanations in small-scale reaction prediction tasks. Preliminary experiments demonstrate that our…

GraphMERT: Efficient and Scalable Distillation of Reliable Knowledge Graphs from Unstructured Data
Margarita Belova, Jiaxin Xiao, Shikhar Tuli, Niraj K. Jha
https://arxiv.org/abs/2510.09580

GraphMERT: Efficient and Scalable Distillation of Reliable Knowledge Graphs from Unstructured Data
Researchers have pursued neurosymbolic artificial intelligence (AI) applications for nearly three decades because symbolic components provide abstraction while neural components provide generalization. Thus, a marriage of the two components can lead to rapid advancements in AI. Yet, the field has not realized this promise since most neurosymbolic AI frameworks fail to scale. In addition, the implicit representations and approximate reasoning of neural approaches limit interpretability and trust…

Do All Autoregressive Transformers Remember Facts the Same Way? A Cross-Architecture Analysis of Recall Mechanisms
Minyeong Choe, Haehyun Cho, Changho Seo, Hyunil Kim
https://arxiv.org/abs/2509.08778

Do All Autoregressive Transformers Remember Facts the Same Way? A Cross-Architecture Analysis of Recall Mechanisms
Understanding how Transformer-based language models store and retrieve factual associations is critical for improving interpretability and enabling targeted model editing. Prior work, primarily on GPT-style models, has identified MLP modules in early layers as key contributors to factual recall. However, it remains unclear whether these findings generalize across different autoregressive architectures. To address this, we conduct a comprehensive evaluation of factual recall across several model…

Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability
Haifei Zhang, Patrick Barry, Eduardo Brandao
https://arxiv.org/abs/2510.00773 https://

Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability
In the context of image classification, Concept Bottleneck Models (CBMs) first embed images into a set of human-understandable concepts, followed by an intrinsically interpretable classifier that predicts labels based on these intermediate representations. While CBMs offer a semantically meaningful and interpretable classification pipeline, they often sacrifice predictive performance compared to end-to-end convolutional neural networks. Moreover, the propagation of uncertainty from concept pred…

Functional Groups are All you Need for Chemically Interpretable Molecular Property Prediction
Roshan Balaji, Joe Bobby, Nirav Pravinbhai Bhatt
https://arxiv.org/abs/2509.09619 h…

Functional Groups are All you Need for Chemically Interpretable Molecular Property Prediction
Molecular property prediction using deep learning (DL) models has accelerated drug and materials discovery, but the resulting DL models often lack interpretability, hindering their adoption by chemists. This work proposes developing molecule representations using the concept of Functional Groups (FG) in chemistry. We introduce the Functional Group Representation (FGR) framework, a novel approach to encoding molecules based on their fundamental chemical substructures. Our method integrates two t…

Lightweight Deep Unfolding Networks with Enhanced Robustness for Infrared Small Target Detection
Jingjing Liu, Yinchao Han, Xianchao Xiu, Jianhua Zhang, Wanquan Liu
https://arxiv.org/abs/2509.08205

Lightweight Deep Unfolding Networks with Enhanced Robustness for Infrared Small Target Detection
Infrared small target detection (ISTD) is one of the key techniques in image processing. Although deep unfolding networks (DUNs) have demonstrated promising performance in ISTD due to their model interpretability and data adaptability, existing methods still face significant challenges in parameter lightweightness and noise robustness. In this regard, we propose a highly lightweight framework based on robust principal component analysis (RPCA) called L-RPCANet. Technically, a hierarchical bottl…

ME$^3$-BEV: Mamba-Enhanced Deep Reinforcement Learning for End-to-End Autonomous Driving with BEV-Perception
Siyi Lu, Run Liu, Dongsheng Yang, Lei He
https://arxiv.org/abs/2508.06074

ME$^3$-BEV: Mamba-Enhanced Deep Reinforcement Learning for End-to-End Autonomous Driving with BEV-Perception
Autonomous driving systems face significant challenges in perceiving complex environments and making real-time decisions. Traditional modular approaches, while offering interpretability, suffer from error propagation and coordination issues, whereas end-to-end learning systems can simplify the design but face computational bottlenecks. This paper presents a novel approach to autonomous driving using deep reinforcement learning (DRL) that integrates bird's-eye view (BEV) perception for enhanced …

BlackboxNLP-2025 MIB Shared Task: Exploring Ensemble Strategies for Circuit Localization Methods
Philipp Mondorf, Mingyang Wang, Sebastian Gerstner, Ahmad Dawar Hakimi, Yihong Liu, Leonor Veloso, Shijia Zhou, Hinrich Sch\"utze, Barbara Plank
https://arxiv.org/abs/2510.06811

BlackboxNLP-2025 MIB Shared Task: Exploring Ensemble Strategies for Circuit Localization Methods
The Circuit Localization track of the Mechanistic Interpretability Benchmark (MIB) evaluates methods for localizing circuits within large language models (LLMs), i.e., subnetworks responsible for specific task behaviors. In this work, we investigate whether ensembling two or more circuit localization methods can improve performance. We explore two variants: parallel and sequential ensembling. In parallel ensembling, we combine attribution scores assigned to each edge by different methods-e.g., …

MetaLLMix : An XAI Aided LLM-Meta-learning Based Approach for Hyper-parameters Optimization
Mohammed Tiouti, Mohamed Bal-Ghaoui
https://arxiv.org/abs/2509.09387 https://

MetaLLMix : An XAI Aided LLM-Meta-learning Based Approach for Hyper-parameters Optimization
Effective model and hyperparameter selection remains a major challenge in deep learning, often requiring extensive expertise and computation. While AutoML and large language models (LLMs) promise automation, current LLM-based approaches rely on trial and error and expensive APIs, which provide limited interpretability and generalizability. We propose MetaLLMiX, a zero-shot hyperparameter optimization framework combining meta-learning, explainable AI, and efficient LLM reasoning. By leveraging h…

A Framework for Inherently Safer AGI through Language-Mediated Active Inference
Bo Wen
https://arxiv.org/abs/2508.05766 https://arxiv.org/pdf/2508.05766

A Framework for Inherently Safer AGI through Language-Mediated Active Inference
This paper proposes a novel framework for developing safe Artificial General Intelligence (AGI) by combining Active Inference principles with Large Language Models (LLMs). We argue that traditional approaches to AI safety, focused on post-hoc interpretability and reward engineering, have fundamental limitations. We present an architecture where safety guarantees are integrated into the system's core design through transparent belief representations and hierarchical value alignment. Our framewor…

Revisiting Data Attribution for Influence Functions
Hongbo Zhu, Angelo Cangelosi
https://arxiv.org/abs/2508.07297 https://arxiv.org/pdf/2508.07297

Revisiting Data Attribution for Influence Functions
The goal of data attribution is to trace the model's predictions through the learning algorithm and back to its training data. thereby identifying the most influential training samples and understanding how the model's behavior leads to particular predictions. Understanding how individual training examples influence a model's predictions is fundamental for machine learning interpretability, data debugging, and model accountability. Influence functions, originating from robust statistics, offer …

DeepGraphLog for Layered Neurosymbolic AI
Adem Kikaj, Giuseppe Marra, Floris Geerts, Robin Manhaeve, Luc De Raedt
https://arxiv.org/abs/2509.07665 https://…

DeepGraphLog for Layered Neurosymbolic AI
Neurosymbolic AI (NeSy) aims to integrate the statistical strengths of neural networks with the interpretability and structure of symbolic reasoning. However, current NeSy frameworks like DeepProbLog enforce a fixed flow where symbolic reasoning always follows neural processing. This restricts their ability to model complex dependencies, especially in irregular data structures such as graphs. In this work, we introduce DeepGraphLog, a novel NeSy framework that extends ProbLog with Graph Neural …

Towards Interpretable Deep Neural Networks for Tabular Data
Khawla Elhadri, J\"org Schl\"otterer, Christin Seifert
https://arxiv.org/abs/2509.08617 https://

Towards Interpretable Deep Neural Networks for Tabular Data
Tabular data is the foundation of many applications in fields such as finance and healthcare. Although DNNs tailored for tabular data achieve competitive predictive performance, they are blackboxes with little interpretability. We introduce XNNTab, a neural architecture that uses a sparse autoencoder (SAE) to learn a dictionary of monosemantic features within the latent space used for prediction. Using an automated method, we assign human-interpretable semantics to these features. This allows u…

Medical priority fusion: achieving dual optimization of sensitivity and interpretability in nipt anomaly detection
Xiuqi Ge, Zhibo Yao, Yaosong Du
https://arxiv.org/abs/2509.17924

Medical priority fusion: achieving dual optimization of sensitivity and interpretability in nipt anomaly detection
Clinical machine learning faces a critical dilemma in high-stakes medical applications: algorithms achieving optimal diagnostic performance typically sacrifice the interpretability essential for physician decision-making, while interpretable methods compromise sensitivity in complex scenarios. This paradox becomes particularly acute in non-invasive prenatal testing (NIPT), where missed chromosomal abnormalities carry profound clinical consequences yet regulatory frameworks mandate explainable A…

Towards explainable decision support using hybrid neural models for logistic terminal automation
Riccardo DElia, Alberto Termine, Francesco Flammini
https://arxiv.org/abs/2509.07577

Towards explainable decision support using hybrid neural models for logistic terminal automation
The integration of Deep Learning (DL) in System Dynamics (SD) modeling for transportation logistics offers significant advantages in scalability and predictive accuracy. However, these gains are often offset by the loss of explainability and causal reliability $-$ key requirements in critical decision-making systems. This paper presents a novel framework for interpretable-by-design neural system dynamics modeling that synergizes DL with techniques from Concept-Based Interpretability, Mechanisti…

Scientific Machine Learning with Kolmogorov-Arnold Networks
Salah A. Faroughi, Farinaz Mostajeran, Amin Hamed Mashhadzadeh, Shirko Faroughi
https://arxiv.org/abs/2507.22959 http…

Scientific Machine Learning with Kolmogorov-Arnold Networks
The field of scientific machine learning, which originally utilized multilayer perceptrons (MLPs), is increasingly adopting Kolmogorov-Arnold Networks (KANs) for data encoding. This shift is driven by the limitations of MLPs, including poor interpretability, fixed activation functions, and difficulty capturing localized or high-frequency features. KANs address these issues with enhanced interpretability and flexibility, enabling more efficient modeling of complex nonlinear interactions and effe…

IBN: An Interpretable Bidirectional-Modeling Network for Multivariate Time Series Forecasting with Variable Missing
Shusen Ma, Tianhao Zhang, Qijiu Xia, Yun-Bo Zhao
https://arxiv.org/abs/2509.07725

IBN: An Interpretable Bidirectional-Modeling Network for Multivariate Time Series Forecasting with Variable Missing
Multivariate time series forecasting (MTSF) often faces challenges from missing variables, which hinder conventional spatial-temporal graph neural networks in modeling inter-variable correlations. While GinAR addresses variable missing using attention-based imputation and adaptive graph learning for the first time, it lacks interpretability and fails to capture more latent temporal patterns due to its simple recursive units (RUs). To overcome these limitations, we propose the Interpretable Bidi…

Introspection in Learned Semantic Scene Graph Localisation
Manshika Charvi Bissessur, Efimia Panagiotaki, Daniele De Martini
https://arxiv.org/abs/2510.07053 https://

Introspection in Learned Semantic Scene Graph Localisation
This work investigates how semantics influence localisation performance and robustness in a learned self-supervised, contrastive semantic localisation framework. After training a localisation network on both original and perturbed maps, we conduct a thorough post-hoc introspection analysis to probe whether the model filters environmental noise and prioritises distinctive landmarks over routine clutter. We validate various interpretability methods and present a comparative reliability analysis. …