Explainable Artificial Intelligence (XAI)

Derniers papiers

• Breaking the Gradient Barrier: Unveiling Large Language Models for Strategic Classification

  Xinpeng Lv, Yunxin Mao, Haoxuan Li, Ke Liang, Jinxuan Yang, Wanrong Huang, Haoang Chi, Huan Chen, Long Lan, Yuanlong Chen, Wenjing Yang, Haotian Wang · 11 novembre 2025

  Strategic classification~(SC) explores how individuals or entities modify their features strategically to achieve favorable classification outcomes. However, existing SC methods, which are largely based on linear models or shallow neural networks, face significant limitations in terms of scalability…

• Flexible Concept Bottleneck Model

  Xingbo Du, Qiantong Dou, Lei Fan, Rui Zhang · 11 novembre 2025

  Concept bottleneck models (CBMs) improve neural network interpretability by introducing an intermediate layer that maps human-understandable concepts to predictions. Recent work has explored the use of vision-language models (VLMs) to automate concept selection and annotation. However, existing VLM-…

• Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability

  Usha Bhalla, Alex Oesterling, Claudio Mayrink Verdun, Himabindu Lakkaraju, Flavio P. Calmon · 11 novembre 2025

  Translating the internal representations and computations of models into concepts that humans can understand is a key goal of interpretability. While recent dictionary learning methods such as Sparse Autoencoders (SAEs) provide a promising route to discover human-interpretable features, they suffer …

• Non-Negative Stiefel Approximating Flow: Orthogonalish Matrix Optimization for Interpretable Embeddings

  Brian B. Avants (Department of Radiology,Medical Imaging University of Virginia, Charlottesville, VA), Nicholas J. Tustison (Department of Radiology,Medical Imaging University of Virginia, Charlottesville, VA), James R Stone (Department of Radiology,Medical Imaging University of Virginia, Charlottesville, VA) · 11 novembre 2025

  Interpretable representation learning is a central challenge in modern machine learning, particularly in high-dimensional settings such as neuroimaging, genomics, and text analysis. Current methods often struggle to balance the competing demands of interpretability and model flexibility, limiting th…

• Beyond Softmax: Dual-Branch Sigmoid Architecture for Accurate Class Activation Maps

  Yoojin Oh, Junhyug Noh · 11 novembre 2025

  Class Activation Mapping (CAM) and its extensions have become indispensable tools for visualizing the evidence behind deep network predictions. However, by relying on a final softmax classifier, these methods suffer from two fundamental distortions: additive logit shifts that arbitrarily bias import…

• How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence

  Hongzhe Du, Weikai Li, Min Cai, Karim Saraipour, Zimin Zhang, Himabindu Lakkaraju, Yizhou Sun, Shichang Zhang · 11 novembre 2025

  Post-training is essential for the success of large language models (LLMs), transforming pre-trained base models into more useful and aligned post-trained models. While plenty of works have studied post-training algorithms and evaluated post-training models by their outputs, it remains understudied …

• Quriosity: Analyzing Human Questioning Behavior and Causal Inquiry through Curiosity-Driven Queries

  Roberto Ceraolo, Dmitrii Kharlapenko, Ahmad Khan, Am\'elie Reymond, Punya Syon Pandey, Rada Mihalcea, Bernhard Sch\"olkopf, Mrinmaya Sachan, Zhijing Jin · 11 novembre 2025

  Recent progress in Large Language Model (LLM) technology has changed our role in interacting with these models. Instead of primarily testing these models with questions we already know answers to, we are now using them for queries where the answers are unknown to us, driven by human curiosity. This …

• Rank-1 LoRAs Encode Interpretable Reasoning Signals

  Jake Ward, Paul Riechers, Adam Shai · 11 novembre 2025

  Reasoning models leverage inference-time compute to significantly enhance the performance of language models on difficult logical tasks, and have become a dominating paradigm in frontier LLMs. Despite their wide adoption, the mechanisms underpinning the enhanced performance of these reasoning models…

• Approximating Shapley Explanations in Reinforcement Learning

  Daniel Beechey, \"Ozg\"ur \c{S}im\c{s}ek · 11 novembre 2025

  Reinforcement learning has achieved remarkable success in complex decision-making environments, yet its lack of transparency limits its deployment in practice, especially in safety-critical settings. Shapley values from cooperative game theory provide a principled framework for explaining reinforcem…

• Counterfactual Explanation for Multivariate Time Series Forecasting with Exogenous Variables

  Keita Kinjo · 11 novembre 2025

  Currently, machine learning is widely used across various domains, including time series data analysis. However, some machine learning models function as black boxes, making interpretability a critical concern. One approach to address this issue is counterfactual explanation (CE), which aims to prov…

• TriShGAN: Enhancing Sparsity and Robustness in Multivariate Time Series Counterfactuals Explanation

  Hongnan Ma, Yiwei Shi, Guanxiong Sun, Mengyue Yang, Weiru Liu · 11 novembre 2025

  In decision-making processes, stakeholders often rely on counterfactual explanations, which provide suggestions about what should be changed in the queried instance to alter the outcome of an AI system. However, generating these explanations for multivariate time series presents challenges due to th…

• Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse Autoencoder

  Zhen Xu, Zhen Tan, Song Wang, Kaidi Xu, Tianlong Chen · 11 novembre 2025

  Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models (LLMs) by decomposing token activations into combinations of human-understandable features. While SAEs provide crucial insights into LLM explanations, their practical adoption faces a fundamental challe…

• Consistency Is Not Always Correct: Towards Understanding the Role of Exploration in Post-Training Reasoning

  Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Bo Xue, Qingfu Zhang, Hau-San Wong, Taiji Suzuki · 11 novembre 2025

  Foundation models exhibit broad knowledge but limited task-specific reasoning, motivating post-training strategies such as RLVR and inference scaling with outcome or process reward models (ORM/PRM). While recent work highlights the role of exploration and entropy stability in improving pass@K, empir…

• ProRefine: Inference-Time Prompt Refinement with Textual Feedback

  Deepak Pandita, Tharindu Cyril Weerasooriya, Ankit Parag Shah, Isabelle Diana May-Xin Ng, Christopher M. Homan, Wei Wei · 10 novembre 2025

  Agentic workflows, where multiple AI agents collaborate to accomplish complex tasks like reasoning or planning, play a substantial role in many cutting-edge commercial applications, and continue to fascinate researchers across fields for their potential to accomplish expensive, complex tasks that, u…

• Performative Validity of Recourse Explanations

  Gunnar K\"onig, Hidde Fokkema, Timo Freiesleben, Celestine Mendler-D\"unner, Ulrike von Luxburg · 10 novembre 2025

  When applicants get rejected by an algorithmic decision system, recourse explanations provide actionable suggestions for how to change their input features to get a positive evaluation. A crucial yet overlooked phenomenon is that recourse explanations are performative: When many applicants act accor…

• Cleaning Maintenance Logs with LLM Agents for Improved Predictive Maintenance

  Valeriu Dimidov, Faisal Hawlader, Sasan Jafarnejad, Rapha\"el Frank · 10 novembre 2025

  Economic constraints, limited availability of datasets for reproducibility and shortages of specialized expertise have long been recognized as key challenges to the adoption and advancement of predictive maintenance (PdM) in the automotive sector. Recent progress in large language models (LLMs) pres…

• Machine Learning Algorithms in Statistical Modelling Bridging Theory and Application

  A. Ganapathi Rao, Sathish Krishna Anumula, Aditya Kumar Singh, Renukhadevi M, Y. Jeevan Nagendra Kumar, Tammineni Rama Tulasi · 10 novembre 2025

  It involves the completely novel ways of integrating ML algorithms with traditional statistical modelling that has changed the way we analyze data, do predictive analytics or make decisions in the fields of the data. In this paper, we study some ML and statistical model connections to understand way…

• Unlocking the Black Box: A Five-Dimensional Framework for Evaluating Explainable AI in Credit Risk

  Rongbin Ye, Jiaqi Chen · 10 novembre 2025

  The financial industry faces a significant challenge modeling and risk portfolios: balancing the predictability of advanced machine learning models, neural network models, and explainability required by regulatory entities (such as Office of the Comptroller of the Currency, Consumer Financial Protec…

• Minimal and Mechanistic Conditions for Behavioral Self-Awareness in LLMs

  Matthew Bozoukov, Matthew Nguyen, Shubkarman Singh, Bart Bussmann, Patrick Leask · 10 novembre 2025

  Recent studies have revealed that LLMs can exhibit behavioral self-awareness: the ability to accurately describe or predict their own learned behaviors without explicit supervision. This capability raises safety concerns as it may, for example, allow models to better conceal their true abilities dur…

• Towards Scalable Meta-Learning of near-optimal Interpretable Models via Synthetic Model Generations

  Kyaw Hpone Myint, Zhe Wu, Alexandre G. R. Day, Giri Iyengar · 7 novembre 2025

  Decision trees are widely used in high-stakes fields like finance and healthcare due to their interpretability. This work introduces an efficient, scalable method for generating synthetic pre-training data to enable meta-learning of decision trees. Our approach samples near-optimal decision trees sy…

• Addressing divergent representations from causal interventions on neural networks

  Satchel Grant, Simon Jerome Han, Alexa Tartaglini, Christopher Potts · 7 novembre 2025

  A common approach to mechanistic interpretability is to causally manipulate model representations via targeted interventions in order to understand what those representations encode. Here we ask whether such interventions create out-of-distribution (divergent) representations, and whether this raise…

• KnowThyself: An Agentic Assistant for LLM Interpretability

  Suraj Prasai, Mengnan Du, Ying Zhang, Fan Yang · 7 novembre 2025

  We develop KnowThyself, an agentic assistant that advances large language model (LLM) interpretability. Existing tools provide useful insights but remain fragmented and code-intensive. KnowThyself consolidates these capabilities into a chat-based interface, where users can upload models, pose natura…

• Riesz Regression As Direct Density Ratio Estimation

  Masahiro Kato · 7 novembre 2025

  Riesz regression has garnered attention as a tool in debiased machine learning for causal and structural parameter estimation (Chernozhukov et al., 2021). This study shows that Riesz regression is closely related to direct density-ratio estimation (DRE) in important cases, including average treat- m…

• Explanations Go Linear: Interpretable and Individual Latent Encoding for Post-hoc Explainability

  Simone Piaggesi, Riccardo Guidotti, Fosca Giannotti, Dino Pedreschi · 7 novembre 2025

  Post-hoc explainability is essential for understanding black-box machine learning models. Surrogate-based techniques are widely used for local and global model-agnostic explanations but have significant limitations. Local surrogates capture non-linearities but are computationally expensive and sensi…

• TathyaNyaya and FactLegalLlama: Advancing Factual Judgment Prediction and Explanation in the Indian Legal Context

  Shubham Kumar Nigam, Balaramamahanthi Deepak Patnaik, Shivam Mishra, Noel Shallum, Kripabandhu Ghosh, Arnab Bhattacharya · 7 novembre 2025

  In the landscape of Fact-based Judgment Prediction and Explanation (FJPE), reliance on factual data is essential for developing robust and realistic AI-driven decision-making tools. This paper introduces TathyaNyaya, the largest annotated dataset for FJPE tailored to the Indian legal context, encomp…