Tootfinder

Pragmatic Policy Development via Interpretable Behavior Cloning
Anton Matsson, Yaochen Rao, Heather J. Litman, Fredrik D. Johansson
https://arxiv.org/abs/2507.17056

Pragmatic Policy Development via Interpretable Behavior Cloning
Offline reinforcement learning (RL) holds great promise for deriving optimal policies from observational data, but challenges related to interpretability and evaluation limit its practical use in safety-critical domains. Interpretability is hindered by the black-box nature of unconstrained RL policies, while evaluation -- typically performed off-policy -- is sensitive to large deviations from the data-collecting behavior policy, especially when using methods based on importance sampling. To add…

TRUST: Transparent, Robust and Ultra-Sparse Trees
Albert Dorador
https://arxiv.org/abs/2506.15791 https://arxiv.org/pdf/2506.15791

TRUST: Transparent, Robust and Ultra-Sparse Trees
Piecewise-constant regression trees remain popular for their interpretability, yet often lag behind black-box models like Random Forest in predictive accuracy. In this work, we introduce TRUST (Transparent, Robust, and Ultra-Sparse Trees), a novel regression tree model that combines the accuracy of Random Forests with the interpretability of shallow decision trees and sparse linear models. TRUST further enhances transparency by leveraging Large Language Models to generate tailored, user-friendl…

Faithful, Interpretable Chest X-ray Diagnosis with Anti-Aliased B-cos Networks
Marcel Kleinmann, Shashank Agnihotri, Margret Keuper
https://arxiv.org/abs/2507.16761

Faithful, Interpretable Chest X-ray Diagnosis with Anti-Aliased B-cos Networks
Faithfulness and interpretability are essential for deploying deep neural networks (DNNs) in safety-critical domains such as medical imaging. B-cos networks offer a promising solution by replacing standard linear layers with a weight-input alignment mechanism, producing inherently interpretable, class-specific explanations without post-hoc methods. While maintaining diagnostic performance competitive with state-of-the-art DNNs, standard B-cos models suffer from severe aliasing artifacts in thei…

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack)
Elija Perrier
https://arxiv.org/abs/2506.17846 https://…

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack)
This position paper argues that formal optimal control theory should be central to AI alignment research, offering a distinct perspective from prevailing AI safety and security approaches. While recent work in AI safety and mechanistic interpretability has advanced formal methods for alignment, they often fall short of the generalisation required of control frameworks for other technologies. There is also a lack of research into how to render different alignment/control protocols interoperable.…

eX-NIDS: A Framework for Explainable Network Intrusion Detection Leveraging Large Language Models
Paul R. B. Houssel, Siamak Layeghy, Priyanka Singh, Marius Portmann
https://arxiv.org/abs/2507.16241

eX-NIDS: A Framework for Explainable Network Intrusion Detection Leveraging Large Language Models
This paper introduces eX-NIDS, a framework designed to enhance interpretability in flow-based Network Intrusion Detection Systems (NIDS) by leveraging Large Language Models (LLMs). In our proposed framework, flows labelled as malicious by NIDS are initially processed through a module called the Prompt Augmenter. This module extracts contextual information and Cyber Threat Intelligence (CTI)-related knowledge from these flows. This enriched, context-specific data is then integrated with an input…

LOCOFY Large Design Models -- Design to code conversion solution
Sohaib Muhammad, Ashwati Vipin, Karan Shetti, Honey Mittal
https://arxiv.org/abs/2507.16208

LOCOFY Large Design Models -- Design to code conversion solution
Despite rapid advances in Large Language Models and Multimodal Large Language Models (LLMs), numerous challenges related to interpretability, scalability, resource requirements and repeatability remain, related to their application in the design-to-code space. To address this, we introduce the Large Design Models (LDMs) paradigm specifically trained on designs and webpages to enable seamless conversion from design-to-code. We have developed a training and inference pipeline by incorporating dat…

VLM-UDMC: VLM-Enhanced Unified Decision-Making and Motion Control for Urban Autonomous Driving
Haichao Liu, Haoren Guo, Pei Liu, Benshan Ma, Yuxiang Zhang, Jun Ma, Tong Heng Lee
https://arxiv.org/abs/2507.15266

VLM-UDMC: VLM-Enhanced Unified Decision-Making and Motion Control for Urban Autonomous Driving
Scene understanding and risk-aware attentions are crucial for human drivers to make safe and effective driving decisions. To imitate this cognitive ability in urban autonomous driving while ensuring the transparency and interpretability, we propose a vision-language model (VLM)-enhanced unified decision-making and motion control framework, named VLM-UDMC. This framework incorporates scene reasoning and risk-aware insights into an upper-level slow system, which dynamically reconfigures the optim…

Structural DID with ML: Theory, Simulation, and a Roadmap for Applied Research
Yile Yu, Anzhi Xu, Yi Wang
https://arxiv.org/abs/2507.15899 https://

Structural DID with ML: Theory, Simulation, and a Roadmap for Applied Research
Causal inference in observational panel data has become a central concern in economics,policy analysis,and the broader social sciences.To address the core contradiction where traditional difference-in-differences (DID) struggles with high-dimensional confounding variables in observational panel data,while machine learning (ML) lacks causal structure interpretability,this paper proposes an innovative framework called S-DIDML that integrates structural identification with high-dimensional estimat…

Modeling and Visualization Reasoning for Stakeholders in Education and Industry Integration Systems: Research on Structured Synthetic Dialogue Data Generation Based on NIST Standards
Wei Meng
https://arxiv.org/abs/2506.16952

Modeling and Visualization Reasoning for Stakeholders in Education and Industry Integration Systems: Research on Structured Synthetic Dialogue Data Generation Based on NIST Standards
This study addresses the structural complexity and semantic ambiguity in stakeholder interactions within the Education-Industry Integration (EII) system. The scarcity of real interview data, absence of structured variable modeling, and lack of interpretability in inference mechanisms have limited the analytical accuracy and policy responsiveness of EII research. To resolve these challenges, we propose a structural modeling paradigm based on the National Institute of Standards and Technology (NI…

Diffusion-based Counterfactual Augmentation: Towards Robust and Interpretable Knee Osteoarthritis Grading
Zhe Wang, Yuhua Ru, Aladine Chetouani, Tina Shiang, Fang Chen, Fabian Bauer, Liping Zhang, Didier Hans, Rachid Jennane, William Ewing Palmer, Mohamed Jarraya, Yung Hsin Chen
https://arxiv.org/abs/2506.15748

Diffusion-based Counterfactual Augmentation: Towards Robust and Interpretable Knee Osteoarthritis Grading
Automated grading of Knee Osteoarthritis (KOA) from radiographs is challenged by significant inter-observer variability and the limited robustness of deep learning models, particularly near critical decision boundaries. To address these limitations, this paper proposes a novel framework, Diffusion-based Counterfactual Augmentation (DCA), which enhances model robustness and interpretability by generating targeted counterfactual examples. The method navigates the latent space of a diffusion model…

Stochastically Structured Reservoir Computers for Financial and Economic System Identification
Lendy Banegas, Fredy Vides
https://arxiv.org/abs/2507.17115 https://

Stochastically Structured Reservoir Computers for Financial and Economic System Identification
This paper introduces a methodology for identifying and simulating financial and economic systems using stochastically structured reservoir computers (SSRCs). The proposed framework leverages structure-preserving embeddings and graph-informed coupling matrices to model inter-agent dynamics with enhanced interpretability. A constrained optimization scheme ensures that the learned models satisfy both stochastic and structural constraints. Two empirical case studies, a dynamic behavioral model of …

EndoFinder: Online Lesion Retrieval for Explainable Colorectal Polyp Diagnosis Leveraging Latent Scene Representations
Ruijie Yang, Yan Zhu, Peiyao Fu, Yizhe Zhang, Zhihua Wang, Quanlin Li, Pinghong Zhou, Xian Yang, Shuo Wang
https://arxiv.org/abs/2507.17323

EndoFinder: Online Lesion Retrieval for Explainable Colorectal Polyp Diagnosis Leveraging Latent Scene Representations
Colorectal cancer (CRC) remains a leading cause of cancer-related mortality, underscoring the importance of timely polyp detection and diagnosis. While deep learning models have improved optical-assisted diagnostics, they often demand extensive labeled datasets and yield "black-box" outputs with limited interpretability. In this paper, we propose EndoFinder, an online polyp retrieval framework that leverages multi-view scene representations for explainable and scalable CRC diagnosis. First, we …

Interpreting CFD Surrogates through Sparse Autoencoders
Yeping Hu, Shusen Liu
https://arxiv.org/abs/2507.16069 https://arxiv.org/pdf/2507.16069

Interpreting CFD Surrogates through Sparse Autoencoders
Learning-based surrogate models have become a practical alternative to high-fidelity CFD solvers, but their latent representations remain opaque and hinder adoption in safety-critical or regulation-bound settings. This work introduces a posthoc interpretability framework for graph-based surrogate models used in computational fluid dynamics (CFD) by leveraging sparse autoencoders (SAEs). By obtaining an overcomplete basis in the node embedding space of a pretrained surrogate, the method extracts…

Deep Unfolding Network for Nonlinear Multi-Frequency Electrical Impedance Tomography
Giovanni S. Alberti, Damiana Lazzaro, Serena Morigi, Luca Ratti, Matteo Santacesaria
https://arxiv.org/abs/2507.16678

Deep Unfolding Network for Nonlinear Multi-Frequency Electrical Impedance Tomography
Multi-frequency Electrical Impedance Tomography (mfEIT) represents a promising biomedical imaging modality that enables the estimation of tissue conductivities across a range of frequencies. Addressing this challenge, we present a novel variational network, a model-based learning paradigm that strategically merges the advantages and interpretability of classical iterative reconstruction with the power of deep learning. This approach integrates graph neural networks (GNNs) within the iterative P…

Decoding Translation-Related Functional Sequences in 5'UTRs Using Interpretable Deep Learning Models
Yuxi Lin, Yaxue Fang, Zehong Zhang, Zhouwu Liu, Siyun Zhong, Fulong Yu
https://arxiv.org/abs/2507.16801

Decoding Translation-Related Functional Sequences in 5'UTRs Using Interpretable Deep Learning Models
Understanding how 5' untranslated regions (5'UTRs) regulate mRNA translation is critical for controlling protein expression and designing effective therapeutic mRNAs. While recent deep learning models have shown promise in predicting translational efficiency from 5'UTR sequences, most are constrained by fixed input lengths and limited interpretability. We introduce UTR-STCNet, a Transformer-based architecture for flexible and biologically grounded modeling of variable-length 5'UTRs. UTR-STCNet …

User-Guided Force-Directed Graph Layout
Hasan Balci, Augustin Luna
https://arxiv.org/abs/2506.15860 https://arxiv.org/pdf/2506.15860

User-Guided Force-Directed Graph Layout
Visual analysis of relational data is essential for many real-world analytics tasks, with layout quality being key to interpretability. However, existing layout algorithms often require users to navigate complex parameters to express their intent. We present a user-guided force-directed layout approach that enables intuitive control through freehand sketching. Our method uses classical image analysis techniques to extract structural information from sketches, which is then used to generate posi…

Graph-Coarsening for Machine Learning Coarse-grained Molecular Dynamics
Soumya Mondal, Subhanu Halder, Debarchan Basu, Sandeep Kumar, Tarak Karmakar
https://arxiv.org/abs/2507.16531

Graph-Coarsening for Machine Learning Coarse-grained Molecular Dynamics
Coarse-grained (CG) molecular dynamics (MD) simulations can simulate large molecular complexes over extended timescales by reducing degrees of freedom. A critical step in CG modeling is the selection of the CG mapping algorithm, which directly influences both accuracy and interpretability of the model. Despite progress, the optimal strategy for coarse-graining remains a challenging task, highlighting the necessity for a comprehensive theoretical framework. In this work, we present a graph-based…

Radiological and Biological Dictionary of Radiomics Features: Addressing Understandable AI Issues in Personalized Breast Cancer; Dictionary Version BM1.0
Arman Gorji, Nima Sanati, Amir Hossein Pouria, Somayeh Sadat Mehrnia, Ilker Hacihaliloglu, Arman Rahmim, Mohammad R. Salmanpour
https://arxiv.org/abs/2507.16041

Radiological and Biological Dictionary of Radiomics Features: Addressing Understandable AI Issues in Personalized Breast Cancer; Dictionary Version BM1.0
Radiomics-based AI models show promise for breast cancer diagnosis but often lack interpretability, limiting clinical adoption. This study addresses the gap between radiomic features (RF) and the standardized BI-RADS lexicon by proposing a dual-dictionary framework. First, a Clinically-Informed Feature Interpretation Dictionary (CIFID) was created by mapping 56 RFs to BI-RADS descriptors (shape, margin, internal enhancement) through literature and expert review. The framework was applied to cla…

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…

Revolutionizing Validation and Verification: Explainable Testing Methodologies for Intelligent Automotive Decision-Making Systems
Halit Eris, Stefan Wagner
https://arxiv.org/abs/2506.16876

Revolutionizing Validation and Verification: Explainable Testing Methodologies for Intelligent Automotive Decision-Making Systems
Autonomous Driving Systems (ADS) use complex decision-making (DM) models with multimodal sensory inputs, making rigorous validation and verification (V&V) essential for safety and reliability. These models pose challenges in diagnosing failures, tracing anomalies, and maintaining transparency, with current manual testing methods being inefficient and labor-intensive. This vision paper presents a methodology that integrates explainability, transparency, and interpretability into V&V processes. W…

LUNDIsim: model meshes for flow simulation and scientific data compression benchmarks
Laurent Duval, Fr\'ed\'eric Payan, Christophe Preux, Lauriane Bouard
https://arxiv.org/abs/2508.13636

LUNDIsim: model meshes for flow simulation and scientific data compression benchmarks
The volume of scientific data produced for and by numerical simulation workflows is increasing at an incredible rate. This raises concerns either in computability, interpretability, and sustainability. This is especially noticeable in earth science (geology, meteorology, oceanography, and astronomy), notably with climate studies. We highlight five main evaluation issues: efficiency, discrepancy, diversity, interpretability, availability. Among remedies, lossless and lossy compression techn…

Enhancing Transferability and Consistency in Cross-Domain Recommendations via Supervised Disentanglement
Yuhan Wang, Qing Xie, Zhifeng Bao, Mengzi Tang, Lin Li, Yongjian Liu
https://arxiv.org/abs/2507.17112

Enhancing Transferability and Consistency in Cross-Domain Recommendations via Supervised Disentanglement
Cross-domain recommendation (CDR) aims to alleviate the data sparsity by transferring knowledge across domains. Disentangled representation learning provides an effective solution to model complex user preferences by separating intra-domain features (domain-shared and domain-specific features), thereby enhancing robustness and interpretability. However, disentanglement-based CDR methods employing generative modeling or GNNs with contrastive objectives face two key challenges: (i) pre-separation…

Towards Real-time Structural Dynamics Simulation with Graph-based Digital Twin Modelling
Jun Zhang, Tong Zhang, Ying Wang
https://arxiv.org/abs/2506.18724 …

Towards Real-time Structural Dynamics Simulation with Graph-based Digital Twin Modelling
Precise and timely simulation of a structure's dynamic behavior is crucial for evaluating its performance and assessing its health status. Traditional numerical methods are often limited by high computational costs and low efficiency, while deep learning approaches offer a promising alternative. However, these data-driven methods still face challenges, such as limited physical interpretability and difficulty in adapting to diverse structural configurations. To address these issues, this study p…

Attention-Based Explainability for Structure-Property Relationships
Boris N. Slautin, Utkarsh Pratiush, Yongtao Liu, Hiroshi Funakubo, Vladimir V. Shvartsman, Doru C. Lupascu, Sergei V. Kalinin
https://arxiv.org/abs/2508.15493

Attention-Based Explainability for Structure-Property Relationships
Machine learning methods are emerging as a universal paradigm for constructing correlative structure-property relationships in materials science based on multimodal characterization. However, this necessitates development of methods for physical interpretability of the resulting correlative models. Here, we demonstrate the potential of attention-based neural networks for revealing structure-property relationships and the underlying physical mechanisms, using the ferroelectric properties of PbTi…

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…

Language-Guided Tuning: Enhancing Numeric Optimization with Textual Feedback
Yuxing Lu, Yucheng Hu, Nan Sun, Xukai Zhao
https://arxiv.org/abs/2508.15757 https://

Language-Guided Tuning: Enhancing Numeric Optimization with Textual Feedback
Configuration optimization remains a critical bottleneck in machine learning, requiring coordinated tuning across model architecture, training strategy, feature engineering, and hyperparameters. Traditional approaches treat these dimensions independently and lack interpretability, while recent automated methods struggle with dynamic adaptability and semantic reasoning about optimization decisions. We introduce Language-Guided Tuning (LGT), a novel framework that employs multi-agent Large Langua…

From Atoms to Dynamics: Learning the Committor Without Collective Variables
Sergio Contreras Arredondo, Chenyu Tang, Radu A. Talmazan, Alberto Meg\'ias, Cheng Giuseppe Chen, Christophe Chipot
https://arxiv.org/abs/2507.17700

From Atoms to Dynamics: Learning the Committor Without Collective Variables
This Brief Communication introduces a graph-neural-network architecture built on geometric vector perceptrons to predict the committor function directly from atomic coordinates, bypassing the need for hand-crafted collective variables (CVs). The method offers atom-level interpretability, pinpointing the key atomic players in complex transitions without relying on prior assumptions. Applied across diverse molecular systems, the method accurately infers the committor function and highlights the i…

Physics-guided gated recurrent units for inversion-based feedforward control
Mingdao Lin, Max Bolderman, Mircea Lazar
https://arxiv.org/abs/2507.14052 http…

Physics-guided gated recurrent units for inversion-based feedforward control
Inversion-based feedforward control relies on an accurate model that describes the inverse system dynamics. The gated recurrent unit (GRU), which is a recent architecture in recurrent neural networks, is a strong candidate for obtaining such a model from data. However, due to their black-box nature, GRUs face challenges such as limited interpretability and vulnerability to overfitting. Recently, physics-guided neural networks (PGNNs) have been introduced, which integrate the prior physical mode…

Tree-like Pairwise Interaction Networks
Ronald Richman, Salvatore Scognamiglio, Mario V. W\"uthrich
https://arxiv.org/abs/2508.15678 https://arxiv.org…

Tree-like Pairwise Interaction Networks
Modeling feature interactions in tabular data remains a key challenge in predictive modeling, for example, as used for insurance pricing. This paper proposes the Tree-like Pairwise Interaction Network (PIN), a novel neural network architecture that explicitly captures pairwise feature interactions through a shared feed-forward neural network architecture that mimics the structure of decision trees. PIN enables intrinsic interpretability by design, allowing for direct inspection of interaction e…

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…

Mapping Emotions in the Brain: A Bi-Hemispheric Neural Model with Explainable Deep Learning
David Freire-Obreg\'on, Agnieszka Dubiel, Prasoon Kumar Vinodkumar, Gholamreza Anbarjafari, Dorota Kami\'nska, Modesto Castrill\'on-Santana
https://arxiv.org/abs/2507.12625

Mapping Emotions in the Brain: A Bi-Hemispheric Neural Model with Explainable Deep Learning
Recent advances have shown promise in emotion recognition from electroencephalogram (EEG) signals by employing bi-hemispheric neural architectures that incorporate neuroscientific priors into deep learning models. However, interpretability remains a significant limitation for their application in sensitive fields such as affective computing and cognitive modeling. In this work, we introduce a post-hoc interpretability framework tailored to dual-stream EEG classifiers, extending the Local Interp…

PepThink-R1: LLM for Interpretable Cyclic Peptide Optimization with CoT SFT and Reinforcement Learning
Ruheng Wang, Hang Zhang, Trieu Nguyen, Shasha Feng, Hao-Wei Pang, Xiang Yu, Li Xiao, Peter Zhiping Zhang
https://arxiv.org/abs/2508.14765

PepThink-R1: LLM for Interpretable Cyclic Peptide Optimization with CoT SFT and Reinforcement Learning
Designing therapeutic peptides with tailored properties is hindered by the vastness of sequence space, limited experimental data, and poor interpretability of current generative models. To address these challenges, we introduce PepThink-R1, a generative framework that integrates large language models (LLMs) with chain-of-thought (CoT) supervised fine-tuning and reinforcement learning (RL). Unlike prior approaches, PepThink-R1 explicitly reasons about monomer-level modifications during sequence …

When Bi-interpretability implies Synonymy
Harvey M. Friedman, Albert Visser
https://arxiv.org/abs/2506.01028 https://arxiv.org/pdf/25…

When Bi-interpretability implies Synonymy
Two salient notions of sameness of theories are synonymy, also known as definitional equivalence, and bi-interpretability. Of these two definitional equivalence is the strictest notion. In which cases can we infer synonymy from bi-interpretability? We study this question for the case of sequential theories. Our result is as follows. Suppose that two sequential theories are bi-interpretable and that the interpretations involved in the bi-interpretation are one-dimensional and identity preserving…

Beyond Black Boxes: Enhancing Interpretability of Transformers Trained on Neural Data
Laurence Freeman, Philip Shamash, Vinam Arora, Caswell Barry, Tiago Branco, Eva Dyer
https://arxiv.org/abs/2506.14014

Beyond Black Boxes: Enhancing Interpretability of Transformers Trained on Neural Data
Transformer models have become state-of-the-art in decoding stimuli and behavior from neural activity, significantly advancing neuroscience research. Yet greater transparency in their decision-making processes would substantially enhance their utility in scientific and clinical contexts. Sparse autoencoders offer a promising solution by producing hidden units that respond selectively to specific variables, enhancing interpretability. Here, we introduce SAEs into a neural decoding framework by a…

A Voxel-Wise Uncertainty-Guided Framework for Glioma Segmentation Using Spherical Projection-Based U-Net and Localized Refinement in Multi-Parametric MRI
Zhenyu Yang, Chen Yang, Rihui Zhang, Minbin Chen, Chunhao Wang, Fang-Fang Yin
https://arxiv.org/abs/2507.15622

A Voxel-Wise Uncertainty-Guided Framework for Glioma Segmentation Using Spherical Projection-Based U-Net and Localized Refinement in Multi-Parametric MRI
Purpose: Accurate segmentation of glioma subregions in multi-parametric MRI (MP-MRI) is essential for diagnosis and treatment planning but remains challenging due to tumor heterogeneity and ambiguous boundaries. This study proposes an uncertainty-guided hybrid framework integrating spherical projection-based 2D modeling with targeted 3D refinement to enhance segmentation accuracy and interpretability. Methods: Using the BraTS2020 dataset (369 patients, four-modality MP-MRI), three 2D U-Nets wer…

Understanding Matching Mechanisms in Cross-Encoders
Mathias Vast, Basile Van Cooten, Laure Soulier, Benjamin Piwowarski
https://arxiv.org/abs/2507.14604 ht…

Understanding Matching Mechanisms in Cross-Encoders
Neural IR architectures, particularly cross-encoders, are highly effective models whose internal mechanisms are mostly unknown. Most works trying to explain their behavior focused on high-level processes (e.g., what in the input influences the prediction, does the model adhere to known IR axioms) but fall short of describing the matching process. Instead of Mechanistic Interpretability approaches which specifically aim at explaining the hidden mechanisms of neural models, we demonstrate that mo…

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…

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

SPARC: Concept-Aligned Sparse Autoencoders for Cross-Model and Cross-Modal Interpretability
Ali Nasiri-Sarvi, Hassan Rivaz, Mahdi S. Hosseini
https://arxiv.org/abs/2507.06265

SPARC: Concept-Aligned Sparse Autoencoders for Cross-Model and Cross-Modal Interpretability
Understanding how different AI models encode the same high-level concepts, such as objects or attributes, remains challenging because each model typically produces its own isolated representation. Existing interpretability methods like Sparse Autoencoders (SAEs) produce latent concepts individually for each model, resulting in incompatible concept spaces and limiting cross-model interpretability. To address this, we introduce SPARC (Sparse Autoencoders for Aligned Representation of Concepts), a…

Concept-Based Mechanistic Interpretability Using Structured Knowledge Graphs
Sofiia Chorna, Kateryna Tarelkina, Elo\"ise Berthier, Gianni Franchi
https://arxiv.org/abs/2507.05810

Concept-Based Mechanistic Interpretability Using Structured Knowledge Graphs
While concept-based interpretability methods have traditionally focused on local explanations of neural network predictions, we propose a novel framework and interactive tool that extends these methods into the domain of mechanistic interpretability. Our approach enables a global dissection of model behavior by analyzing how high-level semantic attributes (referred to as concepts) emerge, interact, and propagate through internal model components. Unlike prior work that isolates individual neuro…

Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models
Marouane Il Idrissi, Agathe Fernandes Machado, Arthur Charpentier
https://arxiv.org/abs/2506.13900

Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models
Cooperative game theory has become a cornerstone of post-hoc interpretability in machine learning, largely through the use of Shapley values. Yet, despite their widespread adoption, Shapley-based methods often rest on axiomatic justifications whose relevance to feature attribution remains debatable. In this paper, we revisit cooperative game theory from an interpretability perspective and argue for a broader and more principled use of its tools. We highlight two general families of efficient al…

A Survey of Physics-Informed AI for Complex Urban Systems
En Xu, Huandong Wang, Yunke Zhang, Sibo Li, Yinzhou Tang, Zhilun Zhou, Yuming Lin, Yuan Yuan, Xiaochen Fan, Jingtao Ding, Yong Li
https://arxiv.org/abs/2506.13777

A Survey of Physics-Informed AI for Complex Urban Systems
Urban systems are typical examples of complex systems, where the integration of physics-based modeling with artificial intelligence (AI) presents a promising paradigm for enhancing predictive accuracy, interpretability, and decision-making. In this context, AI excels at capturing complex, nonlinear relationships, while physics-based models ensure consistency with real-world laws and provide interpretable insights. We provide a comprehensive review of physics-informed AI methods in urban applica…

Replaced article(s) found for physics.chem-ph. https://arxiv.org/list/physics.chem-ph/new
[1/1]:
Transferability and interpretability of vibrational normalizing-flow coordinates

ITL-LIME: Instance-Based Transfer Learning for Enhancing Local Explanations in Low-Resource Data Settings
Rehan Raza, Guanjin Wang, Kevin Wong, Hamid Laga, Marco Fisichella
https://arxiv.org/abs/2508.13672

ITL-LIME: Instance-Based Transfer Learning for Enhancing Local Explanations in Low-Resource Data Settings
Explainable Artificial Intelligence (XAI) methods, such as Local Interpretable Model-Agnostic Explanations (LIME), have advanced the interpretability of black-box machine learning models by approximating their behavior locally using interpretable surrogate models. However, LIME's inherent randomness in perturbation and sampling can lead to locality and instability issues, especially in scenarios with limited training data. In such cases, data scarcity can result in the generation of unrealistic…

Prediction is not Explanation: Revisiting the Explanatory Capacity of Mapping Embeddings
Hanna Herasimchyk, Alhassan Abdelhalim, S\"oren Laue, Michaela Regneri
https://arxiv.org/abs/2508.13729

Prediction is not Explanation: Revisiting the Explanatory Capacity of Mapping Embeddings
Understanding what knowledge is implicitly encoded in deep learning models is essential for improving the interpretability of AI systems. This paper examines common methods to explain the knowledge encoded in word embeddings, which are core elements of large language models (LLMs). These methods typically involve mapping embeddings onto collections of human-interpretable semantic features, known as feature norms. Prior work assumes that accurately predicting these semantic features from the wor…

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…

CipherMind: The Longest Codebook in the World
Ming Nie, Zhixiong Yang, Bingsheng Wei
https://arxiv.org/abs/2506.15117 https://arxiv.o…

CipherMind:The Longest Codebook in the World
In recent years, the widespread application of large language models has inspired us to consider using inference for communication encryption. We therefore propose CipherMind, which utilizes intermediate results from deterministic fine-tuning of large model inferences as transmission content. The semantic parameters of large models exhibit characteristics like opaque underlying implementations and weak interpretability, thus enabling their use as an encryption method for data transmission. This…

Trustworthy Tree-based Machine Learning by $MoS_2$ Flash-based Analog CAM with Inherent Soft Boundaries
Bo Wen, Guoyun Gao, Zhicheng Xu, Ruibin Mao, Xiaojuan Qi, X. Sharon Hu, Xunzhao Yin, Can Li
https://arxiv.org/abs/2507.12384

Trustworthy Tree-based Machine Learning by $MoS_2$ Flash-based Analog CAM with Inherent Soft Boundaries
The rapid advancement of artificial intelligence has raised concerns regarding its trustworthiness, especially in terms of interpretability and robustness. Tree-based models like Random Forest and XGBoost excel in interpretability and accuracy for tabular data, but scaling them remains computationally expensive due to poor data locality and high data dependence. Previous efforts to accelerate these models with analog content addressable memory (CAM) have struggled, due to the fact that the diff…

Newfluence: Boosting Model interpretability and Understanding in High Dimensions
Haolin Zou, Arnab Auddy, Yongchan Kwon, Kamiar Rahnama Rad, Arian Maleki
https://arxiv.org/abs/2507.11895

Newfluence: Boosting Model interpretability and Understanding in High Dimensions
The increasing complexity of machine learning (ML) and artificial intelligence (AI) models has created a pressing need for tools that help scientists, engineers, and policymakers interpret and refine model decisions and predictions. Influence functions, originating from robust statistics, have emerged as a popular approach for this purpose. However, the heuristic foundations of influence functions rely on low-dimensional assumptions where the number of parameters $p$ is much smaller than the …

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…

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…

POCO: Scalable Neural Forecasting through Population Conditioning
Yu Duan, Hamza Tahir Chaudhry, Misha B. Ahrens, Christopher D Harvey, Matthew G Perich, Karl Deisseroth, Kanaka Rajan
https://arxiv.org/abs/2506.14957

POCO: Scalable Neural Forecasting through Population Conditioning
Predicting future neural activity is a core challenge in modeling brain dynamics, with applications ranging from scientific investigation to closed-loop neurotechnology. While recent models of population activity emphasize interpretability and behavioral decoding, neural forecasting-particularly across multi-session, spontaneous recordings-remains underexplored. We introduce POCO, a unified forecasting model that combines a lightweight univariate forecaster with a population-level encoder to ca…

Compressed Models are NOT Trust-equivalent to Their Large Counterparts
Rohit Raj Rai, Chirag Kothari, Siddhesh Shelke, Amit Awekar
https://arxiv.org/abs/2508.13533 https://

Compressed Models are NOT Trust-equivalent to Their Large Counterparts
Large Deep Learning models are often compressed before being deployed in a resource-constrained environment. Can we trust the prediction of compressed models just as we trust the prediction of the original large model? Existing work has keenly studied the effect of compression on accuracy and related performance measures. However, performance parity does not guarantee trust-equivalence. We propose a two-dimensional framework for trust-equivalence evaluation. First, interpretability alignment me…

PhishDebate: An LLM-Based Multi-Agent Framework for Phishing Website Detection
Wenhao Li, Selvakumar Manickam, Yung-wey Chong, Shankar Karuppayah
https://arxiv.org/abs/2506.15656 …

PhishDebate: An LLM-Based Multi-Agent Framework for Phishing Website Detection
Phishing websites continue to pose a significant cybersecurity threat, often leveraging deceptive structures, brand impersonation, and social engineering tactics to evade detection. While recent advances in large language models (LLMs) have enabled improved phishing detection through contextual understanding, most existing approaches rely on single-agent classification facing the risks of hallucination and lack interpretability or robustness. To address these limitations, we propose PhishDebate…

Towards Bridging Formal Methods and Human Interpretability
Abhijit Paul, Proma Chowdhury, Kazi Sakib
https://arxiv.org/abs/2506.09759 https://

Towards Bridging Formal Methods and Human Interpretability
Labeled Transition Systems (LTS) are integral to model checking and design repair tools. System engineers frequently examine LTS designs during model checking or design repair to debug, identify inconsistencies, and validate system behavior. Despite LTS's significance, no prior research has examined human comprehension of these designs. To address this, we draw on traditional software engineering and graph theory, identifying 7 key metrics: cyclomatic complexity, state space size, average branc…

This https://arxiv.org/abs/2504.13151 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

MIB: A Mechanistic Interpretability Benchmark
How can we know whether new mechanistic interpretability methods achieve real improvements? In pursuit of lasting evaluation standards, we propose MIB, a Mechanistic Interpretability Benchmark, with two tracks spanning four tasks and five models. MIB favors methods that precisely and concisely recover relevant causal pathways or causal variables in neural language models. The circuit localization track compares methods that locate the model components - and connections between them - most impor…

Physics-Constrained Diffusion Reconstruction with Posterior Correction for Quantitative and Fast PET Imaging
Yucun Hou, Fenglin Zhan, Chenxi Li, Ziquan Yuan, Haoyu Lu, Yue Chen, Yihao Chen, Kexin Wang, Runze Liao, Haoqi Wen, Ganxi Du, Jiaru Ni, Taoran Chen, Jinyue Zhang, Jigang Yang, Jianyong Jiang
https://arxiv.org/abs/2508.14364

Physics-Constrained Diffusion Reconstruction with Posterior Correction for Quantitative and Fast PET Imaging
Deep learning-based reconstruction of positron emission tomography(PET) data has gained increasing attention in recent years. While these methods achieve fast reconstruction,concerns remain regarding quantitative accuracy and the presence of artifacts,stemming from limited model interpretability,data driven dependence, and overfitting risks.These challenges have hindered clinical adoption.To address them,we propose a conditional diffusion model with posterior physical correction (PET-DPC) for P…

A Fully Transformer Based Multimodal Framework for Explainable Cancer Image Segmentation Using Radiology Reports
Enobong Adahada, Isabel Sassoon, Kate Hone, Yongmin Li
https://arxiv.org/abs/2508.13796 …

A Fully Transformer Based Multimodal Framework for Explainable Cancer Image Segmentation Using Radiology Reports
We introduce Med-CTX, a fully transformer based multimodal framework for explainable breast cancer ultrasound segmentation. We integrate clinical radiology reports to boost both performance and interpretability. Med-CTX achieves exact lesion delineation by using a dual-branch visual encoder that combines ViT and Swin transformers, as well as uncertainty aware fusion. Clinical language structured with BI-RADS semantics is encoded by BioClinicalBERT and combined with visual features utilising cro…

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 …

Trans-XFed: An Explainable Federated Learning for Supply Chain Credit Assessment
Jie Shi, Arno P. J. M. Siebes, Siamak Mehrkanoon
https://arxiv.org/abs/2508.13715 https://

Trans-XFed: An Explainable Federated Learning for Supply Chain Credit Assessment
This paper proposes a Trans-XFed architecture that combines federated learning with explainable AI techniques for supply chain credit assessment. The proposed model aims to address several key challenges, including privacy, information silos, class imbalance, non-identically and independently distributed (Non-IID) data, and model interpretability in supply chain credit assessment. We introduce a performance-based client selection strategy (PBCS) to tackle class imbalance and Non-IID problems. T…

A Review and Comparison of Different Sensitivity Analysis Techniques in Practice
Devin Francom, Abigael Nachtsheim
https://arxiv.org/abs/2506.11471 https:/…

A Review and Comparison of Different Sensitivity Analysis Techniques in Practice
There exist many methods for sensitivity analysis readily available to the practitioner. While each seeks to help the modeler answer the same general question -- How do sources of uncertainty or changes in the model inputs relate to uncertainty in the output? -- different methods are associated with different assumptions, constraints, and required resources, leading to conclusions that may vary in interpretability and level of detail. Thus, it is crucial that the practitioner selects the desire…

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…

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…

Bridging Data-Driven and Physics-Based Models: A Consensus Multi-Model Kalman Filter for Robust Vehicle State Estimation
Farid Mafi (University of Waterloo, Waterloo, Canada), Ladan Khoshnevisan (University of Waterloo, Waterloo, Canada), Mohammad Pirani (University of Ottawa, Ottawa, Canada), Amir Khajepour (University of Waterloo, Waterloo, Canada)

Bridging Data-Driven and Physics-Based Models: A Consensus Multi-Model Kalman Filter for Robust Vehicle State Estimation
Vehicle state estimation presents a fundamental challenge for autonomous driving systems, requiring both physical interpretability and the ability to capture complex nonlinear behaviors across diverse operating conditions. Traditional methodologies often rely exclusively on either physics-based or data-driven models, each with complementary strengths and limitations that become most noticeable during critical scenarios. This paper presents a novel consensus multi-model Kalman filter framework t…

Beyond the Black Box: Interpretability of LLMs in Finance
Hariom Tatsat (Barclays), Ariye Shater (Barclays)
https://arxiv.org/abs/2505.24650 https://

Beyond the Black Box: Interpretability of LLMs in Finance
Large Language Models (LLMs) exhibit remarkable capabilities across a spectrum of tasks in financial services, including report generation, chatbots, sentiment analysis, regulatory compliance, investment advisory, financial knowledge retrieval, and summarization. However, their intrinsic complexity and lack of transparency pose significant challenges, especially in the highly regulated financial sector, where interpretability, fairness, and accountability are critical. As far as we are aware, t…

From Black Boxes to Transparent Minds: Evaluating and Enhancing the Theory of Mind in Multimodal Large Language Models
Xinyang Li, Siqi Liu, Bochao Zou, Jiansheng Chen, Huimin Ma
https://arxiv.org/abs/2506.14224

From Black Boxes to Transparent Minds: Evaluating and Enhancing the Theory of Mind in Multimodal Large Language Models
As large language models evolve, there is growing anticipation that they will emulate human-like Theory of Mind (ToM) to assist with routine tasks. However, existing methods for evaluating machine ToM focus primarily on unimodal models and largely treat these models as black boxes, lacking an interpretative exploration of their internal mechanisms. In response, this study adopts an approach based on internal mechanisms to provide an interpretability-driven assessment of ToM in multimodal large …

CytoSAE: Interpretable Cell Embeddings for Hematology
Muhammed Furkan Dasdelen, Hyesu Lim, Michele Buck, Katharina S. G\"otze, Carsten Marr, Steffen Schneider
https://arxiv.org/abs/2507.12464

CytoSAE: Interpretable Cell Embeddings for Hematology
Sparse autoencoders (SAEs) emerged as a promising tool for mechanistic interpretability of transformer-based foundation models. Very recently, SAEs were also adopted for the visual domain, enabling the discovery of visual concepts and their patch-wise attribution to tokens in the transformer model. While a growing number of foundation models emerged for medical imaging, tools for explaining their inferences are still lacking. In this work, we show the applicability of SAEs for hematology. We pr…

A Unified Theory of Compositionality, Modularity, and Interpretability in Markov Decision Processes
Thomas J. Ringstrom, Paul R. Schrater
https://arxiv.org/abs/2506.09499

A Unified Theory of Compositionality, Modularity, and Interpretability in Markov Decision Processes
We introduce Option Kernel Bellman Equations (OKBEs) for a new reward-free Markov Decision Process. Rather than a value function, OKBEs directly construct and optimize a predictive map called a state-time option kernel (STOK) to maximize the probability of completing a goal while avoiding constraint violations. STOKs are compositional, modular, and interpretable initiation-to-termination transition kernels for policies in the Options Framework of Reinforcement Learning. This means: 1) STOKs can…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[2/3]:
Explainability of Large Language Models using SMILE: Statistical Model-agnostic Interpretability ...

Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models
Ling Li, Yao Zhou, Yuxuan Liang, Fugee Tsung, Jiaheng Wei
https://arxiv.org/abs/2506.14674

Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models
Previous methods for image geo-localization have typically treated the task as either classification or retrieval, often relying on black-box decisions that lack interpretability. The rise of large vision-language models (LVLMs) has enabled a rethinking of geo-localization as a reasoning-driven task grounded in visual cues. However, two major challenges persist. On the data side, existing reasoning-focused datasets are primarily based on street-view imagery, offering limited scene diversity and…

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…

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…

Iterative Augmentation with Summarization Refinement (IASR) Evaluation for Unstructured Survey data Modeling and Analysis
Payal Bhattad, Sai Manoj Pudukotai Dinakarrao, Anju Gupta
https://arxiv.org/abs/2507.12126

Iterative Augmentation with Summarization Refinement (IASR) Evaluation for Unstructured Survey data Modeling and Analysis
Text data augmentation is a widely used strategy for mitigating data sparsity in natural language processing (NLP), particularly in low-resource settings where limited samples hinder effective semantic modeling. While augmentation can improve input diversity and downstream interpretability, existing techniques often lack mechanisms to ensure semantic preservation during large-scale or iterative generation, leading to redundancy and instability. This work introduces a principled evaluation frame…

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…

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…

Tactical Decision for Multi-UGV Confrontation with a Vision-Language Model-Based Commander
Li Wang, Qizhen Wu, Lei Chen
https://arxiv.org/abs/2507.11079 ht…

Tactical Decision for Multi-UGV Confrontation with a Vision-Language Model-Based Commander
In multiple unmanned ground vehicle confrontations, autonomously evolving multi-agent tactical decisions from situational awareness remain a significant challenge. Traditional handcraft rule-based methods become vulnerable in the complicated and transient battlefield environment, and current reinforcement learning methods mainly focus on action manipulation instead of strategic decisions due to lack of interpretability. Here, we propose a vision-language model-based commander to address the iss…

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…

Dual-View Disentangled Multi-Intent Learning for Enhanced Collaborative Filtering
Shanfan Zhang, Yongyi Lin, Yuan Rao, Chenlong Zhang
https://arxiv.org/abs/2506.11538

Dual-View Disentangled Multi-Intent Learning for Enhanced Collaborative Filtering
Disentangling user intentions from implicit feedback has become a promising strategy to enhance recommendation accuracy and interpretability. Prior methods often model intentions independently and lack explicit supervision, thus failing to capture the joint semantics that drive user-item interactions. To address these limitations, we propose DMICF, a unified framework that explicitly models interaction-level intent alignment while leveraging structural signals from both user and item perspectiv…

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…

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…

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…

Fine-Grained Chinese Hate Speech Understanding: Span-Level Resources, Coded Term Lexicon, and Enhanced Detection Frameworks
Zewen Bai, Liang Yang, Shengdi Yin, Yuanyuan Sun, Hongfei Lin
https://arxiv.org/abs/2507.11292

Fine-Grained Chinese Hate Speech Understanding: Span-Level Resources, Coded Term Lexicon, and Enhanced Detection Frameworks
The proliferation of hate speech has inflicted significant societal harm, with its intensity and directionality closely tied to specific targets and arguments. In recent years, numerous machine learning-based methods have been developed to detect hateful comments on online platforms automatically. However, research on Chinese hate speech detection lags behind, and interpretability studies face two major challenges: first, the scarcity of span-level fine-grained annotated datasets limits models'…

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…

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…

This https://arxiv.org/abs/2505.14049 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Learning Concept-Driven Logical Rules for Interpretable and Generalizable Medical Image Classification
The pursuit of decision safety in clinical applications highlights the potential of concept-based methods in medical imaging. While these models offer active interpretability, they often suffer from concept leakages, where unintended information within soft concept representations undermines both interpretability and generalizability. Moreover, most concept-based models focus solely on local explanations (instance-level), neglecting the global decision logic (dataset-level). To address these li…

Enhancing Interpretability in Generative Modeling: Statistically Disentangled Latent Spaces Guided by Generative Factors in Scientific Datasets
Arkaprabha Ganguli, Nesar Ramachandra, Julie Bessac, Emil Constantinescu
https://arxiv.org/abs/2507.00298

Enhancing Interpretability in Generative Modeling: Statistically Disentangled Latent Spaces Guided by Generative Factors in Scientific Datasets
This study addresses the challenge of statistically extracting generative factors from complex, high-dimensional datasets in unsupervised or semi-supervised settings. We investigate encoder-decoder-based generative models for nonlinear dimensionality reduction, focusing on disentangling low-dimensional latent variables corresponding to independent physical factors. Introducing Aux-VAE, a novel architecture within the classical Variational Autoencoder framework, we achieve disentanglement with m…

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

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…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[5/5]:
Explainability of Large Language Models using SMILE: Statistical Model-agnostic Interpretability ...

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…

Searching for actual causes: Approximate algorithms with adjustable precision
Samuel Reyd, Ada Diaconescu, Jean-Louis Dessalles
https://arxiv.org/abs/2507.07857

Searching for actual causes: Approximate algorithms with adjustable precision
Causality has gained popularity in recent years. It has helped improve the performance, reliability, and interpretability of machine learning models. However, recent literature on explainable artificial intelligence (XAI) has faced criticism. The classical XAI and causality literature focuses on understanding which factors contribute to which consequences. While such knowledge is valuable for researchers and engineers, it is not what non-expert users expect as explanations. Instead, these users…

This https://arxiv.org/abs/2503.09532 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
Sparse autoencoders (SAEs) are a popular technique for interpreting language model activations, and there is extensive recent work on improving SAE effectiveness. However, most prior work evaluates progress using unsupervised proxy metrics with unclear practical relevance. We introduce SAEBench, a comprehensive evaluation suite that measures SAE performance across eight diverse metrics, spanning interpretability, feature disentanglement and practical applications like unlearning. To enable syst…

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…

TokenSmith: Streamlining Data Editing, Search, and Inspection for Large-Scale Language Model Training and Interpretability
Mohammad Aflah Khan, Ameya Godbole, Johnny Tian-Zheng Wei, Ryan Wang, James Flemings, Krishna Gummadi, Willie Neiswanger, Robin Jia
https://arxiv.org/abs/2507.19419

TokenSmith: Streamlining Data Editing, Search, and Inspection for Large-Scale Language Model Training and Interpretability
Understanding the relationship between training data and model behavior during pretraining is crucial, but existing workflows make this process cumbersome, fragmented, and often inaccessible to researchers. We present TokenSmith, an open-source library for interactive editing, inspection, and analysis of datasets used in Megatron-style pretraining frameworks such as GPT-NeoX, Megatron, and NVIDIA NeMo. TokenSmith supports a wide range of operations including searching, viewing, ingesting, expor…

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 …

An Efficient Approach for Muscle Segmentation and 3D Reconstruction Using Keypoint Tracking in MRI Scan
Mengyuan Liu, Jeongkyu Lee
https://arxiv.org/abs/2507.08690

An Efficient Approach for Muscle Segmentation and 3D Reconstruction Using Keypoint Tracking in MRI Scan
Magnetic resonance imaging (MRI) enables non-invasive, high-resolution analysis of muscle structures. However, automated segmentation remains limited by high computational costs, reliance on large training datasets, and reduced accuracy in segmenting smaller muscles. Convolutional neural network (CNN)-based methods, while powerful, often suffer from substantial computational overhead, limited generalizability, and poor interpretability across diverse populations. This study proposes a training-…

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…

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…

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 …

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…