Tootfinder

This https://arxiv.org/abs/2312.09454 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Uncertainty Quantification in Machine Learning for Biosignal Applications -- A Review
Uncertainty Quantification (UQ) has gained traction in an attempt to improve the interpretability and robustness of machine learning predictions. Specifically (medical) biosignals such as electroencephalography (EEG), electrocardiography (ECG), electrooculography (EOG), and electromyography (EMG) could benefit from good UQ, since these suffer from a poor signal-to-noise ratio, and good human interpretability is pivotal for medical applications. In this paper, we review the state of the art of a…

Bringing Interpretability to Neural Audio Codecs
Samir Sadok, Julien Hauret, \'Eric Bavu
https://arxiv.org/abs/2506.04492 https://

Bringing Interpretability to Neural Audio Codecs
The advent of neural audio codecs has increased in popularity due to their potential for efficiently modeling audio with transformers. Such advanced codecs represent audio from a highly continuous waveform to low-sampled discrete units. In contrast to semantic units, acoustic units may lack interpretability because their training objectives primarily focus on reconstruction performance. This paper proposes a two-step approach to explore the encoding of speech information within the codec tokens…

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…

This https://arxiv.org/abs/2505.13182 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

Information Science Principles of Machine Learning: A Causal Chain Meta-Framework Based on Formalized Information Mapping
[Objective] This study focuses on addressing the current lack of a unified formal theoretical framework in machine learning, as well as the deficiencies in interpretability and ethical safety assurance. [Methods] A formal information model is first constructed, utilizing sets of well-formed formulas to explicitly define the ontological states and carrier mappings of typical components in machine learning. Learnable and processable predicates, along with learning and processing functions, are in…

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 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…

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…

Understanding Mental Models of Generative Conversational Search and The Effect of Interface Transparency
Chadha Degachi, Samuel Kernan Freire, Evangelos Niforatos, Gerd Kortuem
https://arxiv.org/abs/2506.03807

Understanding Mental Models of Generative Conversational Search and The Effect of Interface Transparency
The experience and adoption of conversational search is tied to the accuracy and completeness of users' mental models -- their internal frameworks for understanding and predicting system behaviour. Thus, understanding these models can reveal areas for design interventions. Transparency is one such intervention which can improve system interpretability and enable mental model alignment. While past research has explored mental models of search engines, those of generative conversational search re…

Towards generating more interpretable counterfactuals via concept vectors: a preliminary study on chest X-rays
Bulat Maksudov, Kathleen Curran, Alessandra Mileo
https://arxiv.org/abs/2506.04058

Towards generating more interpretable counterfactuals via concept vectors: a preliminary study on chest X-rays
An essential step in deploying medical imaging models is ensuring alignment with clinical knowledge and interpretability. We focus on mapping clinical concepts into the latent space of generative models to identify Concept Activation Vectors (CAVs). Using a simple reconstruction autoencoder, we link user-defined concepts to image-level features without explicit label training. The extracted concepts are stable across datasets, enabling visual explanations that highlight clinically relevant feat…

Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval
Seongwan Park, Taeklim Kim, Youngjoong Ko
https://arxiv.org/abs/2506.00041

Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval
Despite their strong performance, Dense Passage Retrieval (DPR) models suffer from a lack of interpretability. In this work, we propose a novel interpretability framework that leverages Sparse Autoencoders (SAEs) to decompose previously uninterpretable dense embeddings from DPR models into distinct, interpretable latent concepts. We generate natural language descriptions for each latent concept, enabling human interpretations of both the dense embeddings and the query-document similarity scores…

The Gauss-Markov Adjunction: Categorical Semantics of Residuals in Supervised Learning
Moto Kamiura
https://arxiv.org/abs/2507.02442 https://

The Gauss-Markov Adjunction: Categorical Semantics of Residuals in Supervised Learning
Enhancing the intelligibility and interpretability of machine learning is a crucial task in responding to the demand for Explicability as an AI principle, and in promoting the better social implementation of AI. The aim of our research is to contribute to this improvement by reformulating machine learning models through the lens of category theory, thereby developing a semantic framework for structuring and understanding AI systems. Our categorical modeling in this paper clarifies and formalize…

LLMs for Legal Subsumption in German Employment Contracts
Oliver Wardas, Florian Matthes
https://arxiv.org/abs/2507.01734 https://arx…

LLMs for Legal Subsumption in German Employment Contracts
Legal work, characterized by its text-heavy and resource-intensive nature, presents unique challenges and opportunities for NLP research. While data-driven approaches have advanced the field, their lack of interpretability and trustworthiness limits their applicability in dynamic legal environments. To address these issues, we collaborated with legal experts to extend an existing dataset and explored the use of Large Language Models (LLMs) and in-context learning to evaluate the legality of cla…

DriveMind: A Dual-VLM based Reinforcement Learning Framework for Autonomous Driving
Dawood Wasif, Terrence J Moore, Chandan K Reddy, Jin-Hee Cho
https://arxiv.org/abs/2506.00819

DriveMind: A Dual-VLM based Reinforcement Learning Framework for Autonomous Driving
End-to-end autonomous driving systems map sensor data directly to control commands, but remain opaque, lack interpretability, and offer no formal safety guarantees. While recent vision-language-guided reinforcement learning (RL) methods introduce semantic feedback, they often rely on static prompts and fixed objectives, limiting adaptability to dynamic driving scenes. We present DriveMind, a unified semantic reward framework that integrates: (i) a contrastive Vision-Language Model (VLM) encoder…

Automated Classification of Volcanic Earthquakes Using Transformer Encoders: Insights into Data Quality and Model Interpretability
Y. Suzuki, Y. Yukutake, T. Ohminato, M. Yamasaki, Ahyi Kim
https://arxiv.org/abs/2507.01260

Automated Classification of Volcanic Earthquakes Using Transformer Encoders: Insights into Data Quality and Model Interpretability
Precisely classifying earthquake types is crucial for elucidating the relationship between volcanic earthquakes and volcanic activity. However, traditional methods rely on subjective human judgment, which requires considerable time and effort. To address this issue, we developed a deep learning model using a transformer encoder for a more objective and efficient classification. Tested on Mount Asama's diverse seismic activity, our model achieved high F1 scores (0.930 for volcano tectonic, 0.931…

Identifying Alzheimer's Disease Prediction Strategies of Convolutional Neural Network Classifiers using R2* Maps and Spectral Clustering
Christian Tinauer, Maximilian Sackl, Stefan Ropele, Christian Langkammer
https://arxiv.org/abs/2506.03890

Identifying Alzheimer's Disease Prediction Strategies of Convolutional Neural Network Classifiers using R2* Maps and Spectral Clustering
Deep learning models have shown strong performance in classifying Alzheimer's disease (AD) from R2* maps, but their decision-making remains opaque, raising concerns about interpretability. Previous studies suggest biases in model decisions, necessitating further analysis. This study uses Layer-wise Relevance Propagation (LRP) and spectral clustering to explore classifier decision strategies across preprocessing and training configurations using R2* maps. We trained a 3D convolutional neural net…

This https://arxiv.org/abs/2505.11396 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Finding Counterfactual Evidences for Node Classification
Counterfactual learning is emerging as an important paradigm, rooted in causality, which promises to alleviate common issues of graph neural networks (GNNs), such as fairness and interpretability. However, as in many real-world application domains where conducting randomized controlled trials is impractical, one has to rely on available observational (factual) data to detect counterfactuals. In this paper, we introduce and tackle the problem of searching for counterfactual evidences for the GNN…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[5/9]:
- Neurons: Emulating the Human Visual Cortex Improves Fidelity and Interpretability in fMRI-to-Vide...
Haonan Wang, Qixiang Zhang, Lehan Wang, Xuanqi Huang, Xiaomeng Li

This https://arxiv.org/abs/2505.13182 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

Information Science Principles of Machine Learning: A Causal Chain Meta-Framework Based on Formalized Information Mapping
[Objective] This study focuses on addressing the current lack of a unified formal theoretical framework in machine learning, as well as the deficiencies in interpretability and ethical safety assurance. [Methods] A formal information model is first constructed, utilizing sets of well-formed formulas to explicitly define the ontological states and carrier mappings of typical components in machine learning. Learnable and processable predicates, along with learning and processing functions, are in…

An Efficient and Interpretable Autoregressive Model for High-Dimensional Tensor-Valued Time Series
Yuxi Cai, Lan Li, Yize Wang, Guodong Li
https://arxiv.org/abs/2506.01658

An Efficient and Interpretable Autoregressive Model for High-Dimensional Tensor-Valued Time Series
In autoregressive modeling for tensor-valued time series, Tucker decomposition, when applied to the coefficient tensor, provides a clear interpretation of supervised factor modeling but loses its efficiency rapidly with increasing tensor order. Conversely, canonical polyadic (CP) decomposition maintains efficiency but lacks a precise statistical interpretation. To attain both interpretability and powerful dimension reduction, this paper proposes a novel approach under the supervised factor mode…

FinAI-BERT: A Transformer-Based Model for Sentence-Level Detection of AI Disclosures in Financial Reports
Muhammad Bilal Zafar
https://arxiv.org/abs/2507.01991

FinAI-BERT: A Transformer-Based Model for Sentence-Level Detection of AI Disclosures in Financial Reports
The proliferation of artificial intelligence (AI) in financial services has prompted growing demand for tools that can systematically detect AI-related disclosures in corporate filings. While prior approaches often rely on keyword expansion or document-level classification, they fall short in granularity, interpretability, and robustness. This study introduces FinAI-BERT, a domain-adapted transformer-based language model designed to classify AI-related content at the sentence level within finan…

Interpretable by Design: MH-AutoML for Transparent and Efficient Android Malware Detection without Compromising Performance
Joner Assolin, Gabriel Canto, Diego Kreutz, Eduardo Feitosa, Hendrio Bragan\c{c}a, Angelo Nogueira, Vanderson Rocha
https://arxiv.org/abs/2506.23314

Interpretable by Design: MH-AutoML for Transparent and Efficient Android Malware Detection without Compromising Performance
Malware detection in Android systems requires both cybersecurity expertise and machine learning (ML) techniques. Automated Machine Learning (AutoML) has emerged as an approach to simplify ML development by reducing the need for specialized knowledge. However, current AutoML solutions typically operate as black-box systems with limited transparency, interpretability, and experiment traceability. To address these limitations, we present MH-AutoML, a domain-specific framework for Android malware d…

Feature Integration Spaces: Joint Training Reveals Dual Encoding in Neural Network Representations
Omar Claflin
https://arxiv.org/abs/2507.00269 https://…

Feature Integration Spaces: Joint Training Reveals Dual Encoding in Neural Network Representations
Current sparse autoencoder (SAE) approaches to neural network interpretability assume that activations can be decomposed through linear superposition into sparse, interpretable features. Despite high reconstruction fidelity, SAEs consistently fail to eliminate polysemanticity and exhibit pathological behavioral errors. We propose that neural networks encode information in two complementary spaces compressed into the same substrate: feature identity and feature integration. To test this dual enc…

This https://arxiv.org/abs/2502.18744 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

ZEBRA: Leveraging Model-Behavioral Knowledge for Zero-Annotation Preference Dataset Construction
Recent efforts in LLM alignment have focused on constructing large-scale preference datasets via human or Artificial Intelligence (AI) annotators. However, such approaches rely on instance-wise supervision, incurring substantial annotation cost and limited interpretability. In this paper, we propose ZEBRA - a model behavior-wise zero-annotation framework that constructs preference data by leveraging model behavior knowledge derived from benchmark performances. ZEBRA binarizes response pairs by …

Unsupervised Evolutionary Cell Type Matching via Entropy-Minimized Optimal Transport
Mu Qiao
https://arxiv.org/abs/2505.24759 https://

Unsupervised Evolutionary Cell Type Matching via Entropy-Minimized Optimal Transport
Identifying evolutionary correspondences between cell types across species is a fundamental challenge in comparative genomics and evolutionary biology. Existing approaches often rely on either reference-based matching, which imposes asymmetry by designating one species as the reference, or projection-based matching, which may increase computational complexity and obscure biological interpretability at the cell-type level. Here, we present OT-MESH, an unsupervised computational framework leverag…

Tug-of-war between idiom's figurative and literal meanings in LLMs
Soyoung Oh, Xinting Huang, Mathis Pink, Michael Hahn, Vera Demberg
https://arxiv.org/abs/2506.01723

Tug-of-war between idiom's figurative and literal meanings in LLMs
Idioms present a unique challenge for language models due to their non-compositional figurative meanings, which often strongly diverge from the idiom's literal interpretation. This duality requires a model to learn representing and deciding between the two meanings to interpret an idiom in a figurative sense, or literally. In this paper, we employ tools from mechanistic interpretability to trace how a large pretrained causal transformer (LLama3.2-1B-base) deals with this ambiguity. We localize …

Automated anatomy-based post-processing reduces false positives and improved interpretability of deep learning intracranial aneurysm detection
Jisoo Kim, Chu-Hsuan Lin, Alberto Ceballos-Arroyo, Ping Liu, Huaizu Jiang, Shrikanth Yadav, Qi Wan, Lei Qin, Geoffrey S Young
https://arxiv.org/abs/2507.00832

Automated anatomy-based post-processing reduces false positives and improved interpretability of deep learning intracranial aneurysm detection
Introduction: Deep learning (DL) models can help detect intracranial aneurysms on CTA, but high false positive (FP) rates remain a barrier to clinical translation, despite improvement in model architectures and strategies like detection threshold tuning. We employed an automated, anatomy-based, heuristic-learning hybrid artery-vein segmentation post-processing method to further reduce FPs. Methods: Two DL models, CPM-Net and a deformable 3D convolutional neural network-transformer hybrid (3D-CN…

Constraint-Guided Symbolic Regression for Data-Efficient Kinetic Model Discovery
Miguel \'Angel de Carvalho Servia (Mimi), Ilya Orson Sandoval (Mimi), King Kuok (Mimi), Hii, Klaus Hellgardt, Dongda Zhang, Ehecatl Antonio del Rio Chanona
https://arxiv.org/abs/2507.02730

Constraint-Guided Symbolic Regression for Data-Efficient Kinetic Model Discovery
The industrialization of catalytic processes hinges on the availability of reliable kinetic models for design, optimization, and control. Traditional mechanistic models demand extensive domain expertise, while many data-driven approaches often lack interpretability and fail to enforce physical consistency. To overcome these limitations, we propose the Physics-Informed Automated Discovery of Kinetics (PI-ADoK) framework. By integrating physical constraints directly into a symbolic regression app…

End-to-End Large Portfolio Optimization for Variance Minimization with Neural Networks through Covariance Cleaning
Christian Bongiorno, Efstratios Manolakis, Rosario Nunzio Mantegna
https://arxiv.org/abs/2507.01918

End-to-End Large Portfolio Optimization for Variance Minimization with Neural Networks through Covariance Cleaning
We develop a rotation-invariant neural network that provides the global minimum-variance portfolio by jointly learning how to lag-transform historical returns and how to regularise both the eigenvalues and the marginal volatilities of large equity covariance matrices. This explicit mathematical mapping offers clear interpretability of each module's role, so the model cannot be regarded as a pure black-box. The architecture mirrors the analytical form of the global minimum-variance solution yet …

Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?
Zhuojun Gu, Quan Wang, Shuchu Han
https://arxiv.org/abs/2506.00751

Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?
Recent advances in Large Language Models (LLMs) highlight the need to align their behaviors with human values. A critical, yet understudied, issue is the potential divergence between an LLM's stated preferences (its reported alignment with general principles) and its revealed preferences (inferred from decisions in contextualized scenarios). Such deviations raise fundamental concerns for the interpretability, trustworthiness, reasoning transparency, and ethical deployment of LLMs, particularly …

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…

Hebbian Physics Networks: A Self-Organizing Computational Architecture Based on Local Physical Laws
Gunjan Auti, Hirofumi Daiguji, Gouhei Tanaka
https://arxiv.org/abs/2507.00641

Hebbian Physics Networks: A Self-Organizing Computational Architecture Based on Local Physical Laws
Traditional machine learning approaches in physics rely on global optimization, limiting interpretability and enforcing physical constraints externally. We introduce the Hebbian Physics Network (HPN), a self-organizing computational framework in which learning emerges from local Hebbian updates driven by violations of conservation laws. Grounded in non-equilibrium thermodynamics and inspired by Prigogine/'s theory of dissipative structures, HPNs eliminate the need for global loss functions by e…

This https://arxiv.org/abs/2505.13182 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

Information Science Principles of Machine Learning: A Causal Chain Meta-Framework Based on Formalized Information Mapping
[Objective] This study focuses on addressing the current lack of a unified formal theoretical framework in machine learning, as well as the deficiencies in interpretability and ethical safety assurance. [Methods] A formal information model is first constructed, utilizing sets of well-formed formulas to explicitly define the ontological states and carrier mappings of typical components in machine learning. Learnable and processable predicates, along with learning and processing functions, are in…

Learning Interpretable Rules from Neural Networks: Neurosymbolic AI for Radar Hand Gesture Recognition
Sarah Seifi, Tobias Sukianto, Cecilia Carbonelli, Lorenzo Servadei, Robert Wille
https://arxiv.org/abs/2506.22443

Learning Interpretable Rules from Neural Networks: Neurosymbolic AI for Radar Hand Gesture Recognition
Rule-based models offer interpretability but struggle with complex data, while deep neural networks excel in performance yet lack transparency. This work investigates a neuro-symbolic rule learning neural network named RL-Net that learns interpretable rule lists through neural optimization, applied for the first time to radar-based hand gesture recognition (HGR). We benchmark RL-Net against a fully transparent rule-based system (MIRA) and an explainable black-box model (XentricAI), evaluating a…

This https://arxiv.org/abs/2410.00665 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qbi…

Graph-Based Representation Learning of Neuronal Dynamics and Behavior
Understanding how neuronal networks reorganize in response to external stimuli and give rise to behavior is a central challenge in neuroscience and artificial intelligence. However, existing methods often fail to capture the evolving structure of neural connectivity in ways that capture its relationship to behavior, especially in dynamic, uncertain, or high-dimensional settings with sufficient resolution or interpretability. We introduce the Temporal Attention-enhanced Variational Graph Recurre…

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…

Large Language Models for Statistical Inference: Context Augmentation with Applications to the Two-Sample Problem and Regression
Marc Ratkovic
https://arxiv.org/abs/2506.23862

Large Language Models for Statistical Inference: Context Augmentation with Applications to the Two-Sample Problem and Regression
We introduce context augmentation, a data-augmentation approach that uses large language models (LLMs) to generate contexts around observed strings as a means of facilitating valid frequentist inference. These generated contexts serve to reintroduce uncertainty, incorporate auxiliary information, and facilitate interpretability. For example, in the two-sample test, we compare the log-probability of strings under contexts from its own versus the other group. We show on synthetic data that the me…

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…

This https://arxiv.org/abs/2502.04049 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Towards Explainable Spoofed Speech Attribution and Detection:a Probabilistic Approach for Characterizing Speech Synthesizer Components
We propose an explainable probabilistic framework for characterizing spoofed speech by decomposing it into probabilistic attribute embeddings. Unlike raw high-dimensional countermeasure embeddings, which lack interpretability, the proposed probabilistic attribute embeddings aim to detect specific speech synthesizer components, represented through high-level attributes and their corresponding values. We use these probabilistic embeddings with four classifier back-ends to address two downstream t…

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…

Disentangled representations of microscopy images
Jacopo Dapueto, Vito Paolo Pastore, Nicoletta Noceti, Francesca Odone
https://arxiv.org/abs/2506.20649 ht…

Disentangled representations of microscopy images
Microscopy image analysis is fundamental for different applications, from diagnosis to synthetic engineering and environmental monitoring. Modern acquisition systems have granted the possibility to acquire an escalating amount of images, requiring a consequent development of a large collection of deep learning-based automatic image analysis methods. Although deep neural networks have demonstrated great performance in this field, interpretability, an essential requirement for microscopy image an…

This https://arxiv.org/abs/2503.02041 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCE_…

Interpolating Neural Network-Tensor Decomposition (INN-TD): a scalable and interpretable approach for large-scale physics-based problems
Deep learning has been extensively employed as a powerful function approximator for modeling physics-based problems described by partial differential equations (PDEs). Despite their popularity, standard deep learning models often demand prohibitively large computational resources and yield limited accuracy when scaling to large-scale, high-dimensional physical problems. Their black-box nature further hinders the application in industrial problems where interpretability and high precision are cr…

EAGLE: Efficient Alignment of Generalized Latent Embeddings for Multimodal Survival Prediction with Interpretable Attribution Analysis
Aakash Tripathi, Asim Waqas, Matthew B. Schabath, Yasin Yilmaz, Ghulam Rasool
https://arxiv.org/abs/2506.22446

EAGLE: Efficient Alignment of Generalized Latent Embeddings for Multimodal Survival Prediction with Interpretable Attribution Analysis
Accurate cancer survival prediction requires integration of diverse data modalities that reflect the complex interplay between imaging, clinical parameters, and textual reports. However, existing multimodal approaches suffer from simplistic fusion strategies, massive computational requirements, and lack of interpretability-critical barriers to clinical adoption. We present EAGLE (Efficient Alignment of Generalized Latent Embeddings), a novel deep learning framework that addresses these limitati…

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…

Hecto: Modular Sparse Experts for Adaptive and Interpretable Reasoning
Sanskar Pandey, Ruhaan Chopra, Saad Murtaza Bhat, Ark Abhyudaya
https://arxiv.org/abs/2506.22919

Hecto: Modular Sparse Experts for Adaptive and Interpretable Reasoning
Mixture-of-Experts (MoE) models enable conditional computation by routing inputs to specialized experts, but these experts rely on identical inductive biases, thus limiting representational diversity. This static computation pathway is inefficient for inputs that require different types of reasoning and limits specialization and interpretability. We propose Hecto, a lightweight MoE architecture that leverages architectural heterogeneity by combining a GRU expert for temporal reasoning and an FF…

SABR-Informed Multitask Gaussian Process: A Synthetic-to-Real Framework for Implied Volatility Surface Construction
Jirong Zhuang, Xuan Wu
https://arxiv.org/abs/2506.22888

SABR-Informed Multitask Gaussian Process: A Synthetic-to-Real Framework for Implied Volatility Surface Construction
Constructing the Implied Volatility Surface (IVS) is a challenging task in quantitative finance due to the complexity of real markets and the sparsity of market data. Structural models like Stochastic Alpha Beta Rho (SABR) model offer interpretability and theoretical consistency but lack flexibility, while purely data-driven methods such as Gaussian Process regression can struggle with sparse data. We introduce SABR-Informed Multi-Task Gaussian Process (SABR-MTGP), treating IVS construction as …

Parameter-Free Bio-Inspired Channel Attention for Enhanced Cardiac MRI Reconstruction
Anam Hashmi, Julia Dietlmeier, Kathleen M. Curran, Noel E. O'Connor
https://arxiv.org/abs/2505.23872

Parameter-Free Bio-Inspired Channel Attention for Enhanced Cardiac MRI Reconstruction
Attention is a fundamental component of the human visual recognition system. The inclusion of attention in a convolutional neural network amplifies relevant visual features and suppresses the less important ones. Integrating attention mechanisms into convolutional neural networks enhances model performance and interpretability. Spatial and channel attention mechanisms have shown significant advantages across many downstream tasks in medical imaging. While existing attention modules have proven …

This https://arxiv.org/abs/2410.09795 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qbi…

WGFormer: An SE(3)-Transformer Driven by Wasserstein Gradient Flows for Molecular Ground-State Conformation Prediction
Predicting molecular ground-state conformation (i.e., energy-minimized conformation) is crucial for many chemical applications such as molecular docking and property prediction. Classic energy-based simulation is time-consuming when solving this problem, while existing learning-based methods have advantages in computational efficiency but sacrifice accuracy and interpretability. In this work, we propose a novel and effective method to bridge the energy-based simulation and the learning-based st…

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…

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…

Deep Learning and Explainable AI: New Pathways to Genetic Insights
Chenyu Wang, Chaoying Zuo, Zihan Su, Yuhang Xing, Lu Li, Maojun Wang, Zeyu Zhang
https://arxiv.org/abs/2505.09873

Deep Learning and Explainable AI: New Pathways to Genetic Insights
Deep learning-based AI models have been extensively applied in genomics, achieving remarkable success across diverse applications. As these models gain prominence, there exists an urgent need for interpretability methods to establish trustworthiness in model-driven decisions. For genetic researchers, interpretable insights derived from these models hold significant value in providing novel perspectives for understanding biological processes. Current interpretability analyses in genomics predomi…

Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder
Yingji Zhang, Danilo S. Carvalho, Andr\'e Freitas
https://arxiv.org/abs/2506.20083

Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder
Integrating compositional and symbolic properties into current distributional semantic spaces can enhance the interpretability, controllability, compositionality, and generalisation capabilities of Transformer-based auto-regressive language models (LMs). In this survey, we offer a novel perspective on latent space geometry through the lens of compositional semantics, a direction we refer to as \textit{semantic representation learning}. This direction enables a bridge between symbolic and distri…

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…

MOSS: Multi-Objective Optimization for Stable Rule Sets
Brian Liu, Rahul Mazumder
https://arxiv.org/abs/2506.08030 https://arxiv.org/…

MOSS: Multi-Objective Optimization for Stable Rule Sets
We present MOSS, a multi-objective optimization framework for constructing stable sets of decision rules. MOSS incorporates three important criteria for interpretability: sparsity, accuracy, and stability, into a single multi-objective optimization framework. Importantly, MOSS allows a practitioner to rapidly evaluate the trade-off between accuracy and stability in sparse rule sets in order to select an appropriate model. We develop a specialized cutting plane algorithm in our framework to rapi…

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…

LettinGo: Explore User Profile Generation for Recommendation System
Lu Wang, Di Zhang, Fangkai Yang, Pu Zhao, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Qingwei Lin, Weiwei Deng, Dongmei Zhang, Feng Sun, Qi Zhang
https://arxiv.org/abs/2506.18309

LettinGo: Explore User Profile Generation for Recommendation System
User profiling is pivotal for recommendation systems, as it transforms raw user interaction data into concise and structured representations that drive personalized recommendations. While traditional embedding-based profiles lack interpretability and adaptability, recent advances with large language models (LLMs) enable text-based profiles that are semantically richer and more transparent. However, existing methods often adhere to fixed formats that limit their ability to capture the full diver…

This https://arxiv.org/abs/2505.13182 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

Information Science Principles of Machine Learning: A Causal Chain Meta-Framework Based on Formalized Information Mapping
[Objective] This study focuses on addressing the current lack of a unified formal theoretical framework in machine learning, as well as the deficiencies in interpretability and ethical safety assurance. [Methods] A formal information model is first constructed, utilizing sets of well-formed formulas to explicitly define the ontological states and carrier mappings of typical components in machine learning. Learnable and processable predicates, along with learning and processing functions, are in…

OmniFluids: Unified Physics Pre-trained Modeling of Fluid Dynamics
Rui Zhang, Qi Meng, Han Wan, Yang Liu, Zhi-Ming Ma, Hao Sun
https://arxiv.org/abs/2506.10862

OmniFluids: Unified Physics Pre-trained Modeling of Fluid Dynamics
High-fidelity and efficient simulation of fluid dynamics drive progress in various scientific and engineering applications. Traditional computational fluid dynamics methods offer strong interpretability and guaranteed convergence, but rely on fine spatial and temporal meshes, incurring prohibitive computational costs. Physics-informed neural networks (PINNs) and neural operators aim to accelerate PDE solvers using deep learning techniques. However, PINNs require extensive retraining and careful…

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…

Investigating Stochastic Methods for Prosody Modeling in Speech Synthesis
Paul Mayer, Florian Lux, Alejandro P\'erez-Gonz\'alez-de-Martos, Angelina Elizarova, Lindsey Vanderlyn, Dirk V\"ath, Ngoc Thang Vu
https://arxiv.org/abs/2507.00227

Investigating Stochastic Methods for Prosody Modeling in Speech Synthesis
While generative methods have progressed rapidly in recent years, generating expressive prosody for an utterance remains a challenging task in text-to-speech synthesis. This is particularly true for systems that model prosody explicitly through parameters such as pitch, energy, and duration, which is commonly done for the sake of interpretability and controllability. In this work, we investigate the effectiveness of stochastic methods for this task, including Normalizing Flows, Conditional Flow…

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

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…

Infinite Time Turing Machines and their Applications
Rukmal Weerawarana, Maxwell Braun
https://arxiv.org/abs/2506.05351 https://arxiv…

Infinite Time Turing Machines and their Applications
This work establishes a rigorous theoretical foundation for analyzing deep learning systems by leveraging Infinite Time Turing Machines (ITTMs), which extend classical computation into transfinite ordinal steps. Using ITTMs, we reinterpret modern architectures like Transformers, revealing fundamental limitations in scalability, efficiency, and interpretability. Building on these insights, we propose the Universal State Machine (USM), a novel computational paradigm designed from first principles…

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…

How much is too much? Measuring divergence from Benford's Law with the Equivalent Contamination Proportion (ECP)
Manuel Cano-Rodriguez
https://arxiv.org/abs/2506.09915

How much is too much? Measuring divergence from Benford's Law with the Equivalent Contamination Proportion (ECP)
Conformity with Benford's Law is widely used to detect irregularities in numerical datasets, particularly in accounting, finance, and economics. However, the statistical tools commonly used for this purpose (such as Chi-squared, MAD, or KS) suffer from three key limitations: sensitivity to sample size, lack of interpretability of their scale, and the absence of a common metric that allows for comparison across different statistics. This paper introduces the Equivalent Contamination Proportion (…

MedChat: A Multi-Agent Framework for Multimodal Diagnosis with Large Language Models
Philip Liu, Sparsh Bansal, Jimmy Dinh, Aditya Pawar, Ramani Satishkumar, Shail Desai, Neeraj Gupta, Xin Wang, Shu Hu
https://arxiv.org/abs/2506.07400

MedChat: A Multi-Agent Framework for Multimodal Diagnosis with Large Language Models
The integration of deep learning-based glaucoma detection with large language models (LLMs) presents an automated strategy to mitigate ophthalmologist shortages and improve clinical reporting efficiency. However, applying general LLMs to medical imaging remains challenging due to hallucinations, limited interpretability, and insufficient domain-specific medical knowledge, which can potentially reduce clinical accuracy. Although recent approaches combining imaging models with LLM reasoning have …

Explainable-AI powered stock price prediction using time series transformers: A Case Study on BIST100
Sukru Selim Calik, Andac Akyuz, Zeynep Hilal Kilimci, Kerem Colak
https://arxiv.org/abs/2506.06345

Explainable-AI powered stock price prediction using time series transformers: A Case Study on BIST100
Financial literacy is increasingly dependent on the ability to interpret complex financial data and utilize advanced forecasting tools. In this context, this study proposes a novel approach that combines transformer-based time series models with explainable artificial intelligence (XAI) to enhance the interpretability and accuracy of stock price predictions. The analysis focuses on the daily stock prices of the five highest-volume banks listed in the BIST100 index, along with XBANK and XU100 in…

TensorTouch: Calibration of Tactile Sensors for High Resolution Stress Tensor and Deformation for Dexterous Manipulation
Won Kyung Do, Matthew Strong, Aiden Swann, Boshu Lei, Monroe Kennedy III
https://arxiv.org/abs/2506.08291

TensorTouch: Calibration of Tactile Sensors for High Resolution Stress Tensor and Deformation for Dexterous Manipulation
Advanced dexterous manipulation involving multiple simultaneous contacts across different surfaces, like pinching coins from ground or manipulating intertwined objects, remains challenging for robotic systems. Such tasks exceed the capabilities of vision and proprioception alone, requiring high-resolution tactile sensing with calibrated physical metrics. Raw optical tactile sensor images, while information-rich, lack interpretability and cross-sensor transferability, limiting their real-world u…

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…

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.…

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…

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…

PCA-Guided Quantile Sampling: Preserving Data Structure in Large-Scale Subsampling
Foo Hui-Mean, Yuan-chin Ivan Chang
https://arxiv.org/abs/2506.18249 http…

PCA-Guided Quantile Sampling: Preserving Data Structure in Large-Scale Subsampling
We introduce Principal Component Analysis guided Quantile Sampling (PCA QS), a novel sampling framework designed to preserve both the statistical and geometric structure of large scale datasets. Unlike conventional PCA, which reduces dimensionality at the cost of interpretability, PCA QS retains the original feature space while using leading principal components solely to guide a quantile based stratification scheme. This principled design ensures that sampling remains representative without di…

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…

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…

Domain Knowledge-Enhanced LLMs for Fraud and Concept Drift Detection
Ali \c{S}enol, Garima Agrawal, Huan Liu
https://arxiv.org/abs/2506.21443 https://arxiv.org/pdf/2506.21443 https://arxiv.org/html/2506.21443
arXiv:2506.21443v1 Announce Type: new
Abstract: Detecting deceptive conversations on dynamic platforms is increasingly difficult due to evolving language patterns and Concept Drift (CD)\-i.e., semantic or topical shifts that alter the context or intent of interactions over time. These shifts can obscure malicious intent or mimic normal dialogue, making accurate classification challenging. While Large Language Models (LLMs) show strong performance in natural language tasks, they often struggle with contextual ambiguity and hallucinations in risk\-sensitive scenarios. To address these challenges, we present a Domain Knowledge (DK)\-Enhanced LLM framework that integrates pretrained LLMs with structured, task\-specific insights to perform fraud and concept drift detection. The proposed architecture consists of three main components: (1) a DK\-LLM module to detect fake or deceptive conversations; (2) a drift detection unit (OCDD) to determine whether a semantic shift has occurred; and (3) a second DK\-LLM module to classify the drift as either benign or fraudulent. We first validate the value of domain knowledge using a fake review dataset and then apply our full framework to SEConvo, a multiturn dialogue dataset that includes various types of fraud and spam attacks. Results show that our system detects fake conversations with high accuracy and effectively classifies the nature of drift. Guided by structured prompts, the LLaMA\-based implementation achieves 98\% classification accuracy. Comparative studies against zero\-shot baselines demonstrate that incorporating domain knowledge and drift awareness significantly improves performance, interpretability, and robustness in high\-stakes NLP applications.
toXiv_bot_toot

TrioXpert: An automated incident management framework for microservice system
Yongqian Sun, Yu Luo, Xidao Wen, Yuan Yuan, Xiaohui Nie, Shenglin Zhang, Tong Liu, Xi Luo
https://arxiv.org/abs/2506.10043

TrioXpert: An automated incident management framework for microservice system
Automated incident management plays a pivotal role in large-scale microservice systems. However, many existing methods rely solely on single-modal data (e.g., metrics, logs, and traces) and struggle to simultaneously address multiple downstream tasks, including anomaly detection (AD), failure triage (FT), and root cause localization (RCL). Moreover, the lack of clear reasoning evidence in current techniques often leads to insufficient interpretability. To address these limitations, we propose T…

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…

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…

R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization
Yuante Li, Xu Yang, Xiao Yang, Minrui Xu, Xisen Wang, Weiqing Liu, Jiang Bian
https://arxiv.org/abs/2505.15155

R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization
Financial markets pose fundamental challenges for asset return prediction due to their high dimensionality, non-stationarity, and persistent volatility. Despite advances in large language models and multi-agent systems, current quantitative research pipelines suffer from limited automation, weak interpretability, and fragmented coordination across key components such as factor mining and model innovation. In this paper, we propose R&D-Agent for Quantitative Finance, in short RD-Agent(Q), the fi…

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 ...

Repeton: Structured Bug Repair with ReAct-Guided Patch-and-Test Cycles
Nguyen Phu Vinh, Anh Chung Hoang, Chris Ngo, Truong-Son Hy
https://arxiv.org/abs/2506.08173

Repeton: Structured Bug Repair with ReAct-Guided Patch-and-Test Cycles
Large Language Models (LLMs) have shown strong capabilities in code generation and comprehension, yet their application to complex software engineering tasks often suffers from low precision and limited interpretability. We present Repeton, a fully open-source framework that leverages LLMs for precise and automated code manipulation in real-world Git repositories. Rather than generating holistic fixes, Repeton operates through a structured patch-and-test pipeline: it iteratively diagnoses issue…

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 …

Regional, Lattice and Logical Representations of Neural Networks
Sandro Preto (Federal University of ABC, Brazil), Marcelo Finger (University of Sao Paulo, Brazil)
https://arxiv.org/abs/2506.05834

Regional, Lattice and Logical Representations of Neural Networks
A possible path to the interpretability of neural networks is to (approximately) represent them in the regional format of piecewise linear functions, where regions of inputs are associated to linear functions computing the network outputs. We present an algorithm for the translation of feedforward neural networks with ReLU activation functions in hidden layers and truncated identity activation functions in the output layer. We also empirically investigate the complexity of regional representati…

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 ...

SatelliteFormula: Multi-Modal Symbolic Regression from Remote Sensing Imagery for Physics Discovery
Zhenyu Yu, Mohd. Yamani Idna Idris, Pei Wang, Yuelong Xia, Fei Ma, Rizwan Qureshi
https://arxiv.org/abs/2506.06176

SatelliteFormula: Multi-Modal Symbolic Regression from Remote Sensing Imagery for Physics Discovery
We propose SatelliteFormula, a novel symbolic regression framework that derives physically interpretable expressions directly from multi-spectral remote sensing imagery. Unlike traditional empirical indices or black-box learning models, SatelliteFormula combines a Vision Transformer-based encoder for spatial-spectral feature extraction with physics-guided constraints to ensure consistency and interpretability. Existing symbolic regression methods struggle with the high-dimensional complexity of…

This https://arxiv.org/abs/2506.04047 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

On Support Samples of Next Word Prediction
Language models excel in various tasks by making complex decisions, yet understanding the rationale behind these decisions remains a challenge. This paper investigates \emph{data-centric interpretability} in language models, focusing on the next-word prediction task. Using representer theorem, we identify two types of \emph{support samples}-those that either promote or deter specific predictions. Our findings reveal that being a support sample is an intrinsic property, predictable even before 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…

This https://arxiv.org/abs/2505.24009 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Diversity of Transformer Layers: One Aspect of Parameter Scaling Laws
Transformers deliver outstanding performance across a wide range of tasks and are now a dominant backbone architecture for large language models (LLMs). Their task-solving performance is improved by increasing parameter size, as shown in the recent studies on parameter scaling laws. Although recent mechanistic-interpretability studies have deepened our understanding of the internal behavior of Transformers by analyzing their residual stream, the relationship between these internal mechanisms an…

ResPF: Residual Poisson Flow for Efficient and Physically Consistent Sparse-View CT Reconstruction
Changsheng Fang, Yongtong Liu, Bahareh Morovati, Shuo Han, Yu Shi, Li Zhou, Shuyi Fan, Hengyong Yu
https://arxiv.org/abs/2506.06400

ResPF: Residual Poisson Flow for Efficient and Physically Consistent Sparse-View CT Reconstruction
Sparse-view computed tomography (CT) is a practical solution to reduce radiation dose, but the resulting ill-posed inverse problem poses significant challenges for accurate image reconstruction. Although deep learning and diffusion-based methods have shown promising results, they often lack physical interpretability or suffer from high computational costs due to iterative sampling starting from random noise. Recent advances in generative modeling, particularly Poisson Flow Generative Models (PF…

Lower-dimensional posterior density and cluster summaries for overparameterized Bayesian models
Henrique Bolfarine, Hedibert F. Lopes, Carlos M. Carvalho
https://arxiv.org/abs/2506.09850

Lower-dimensional posterior density and cluster summaries for overparameterized Bayesian models
The usefulness of Bayesian models for density and cluster estimation is well established across multiple literatures. However, there is still a known tension between the use of simpler, more interpretable models and more flexible, complex ones. In this paper, we propose a novel method that integrates these two approaches by projecting the fit of a flexible, over-parameterized model onto a lower-dimensional parametric summary, which serves as a surrogate. This process increases interpretability …