Explainable Artificial Intelligence (XAI)

Derniers papiers

• Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall

  Qianli Wang, Mingyang Wang, Nils Feldhus, Simon Ostermann, Yuan Cao, Hinrich Sch\"utze, Sebastian M\"oller, Vera Schmitt · 5 janvier 2026

  Quantization methods are widely used to accelerate inference and streamline the deployment of large language models (LLMs). Although quantization's effects on various LLM capabilities have been extensively studied, one critical area remains underexplored: factual knowledge recall (FKR), the process …

• IRPO: Scaling the Bradley-Terry Model via Reinforcement Learning

  Haonan Song, Qingchen Xie, Huan Zhu, Feng Xiao, Luxi Xing, Fuzhen Li, Liu Kang, Feng Jiang, Zhiyong Zheng, Fan Yang · 5 janvier 2026

  Generative Reward Models (GRMs) have attracted considerable research interest in reward modeling due to their interpretability, inference-time scalability, and potential for refinement through reinforcement learning (RL). However, widely used pairwise GRMs create a computational bottleneck when inte…

• Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation

  Qianli Wang, Van Bach Nguyen, Yihong Liu, Fedor Splitt, Nils Feldhus, Christin Seifert, Hinrich Sch\"utze, Sebastian M\"oller, Vera Schmitt · 5 janvier 2026

  Counterfactuals refer to minimally edited inputs that cause a model's prediction to change, serving as a promising approach to explaining the model's behavior. Large language models (LLMs) excel at generating English counterfactuals and demonstrate multilingual proficiency. However, their effectiven…

• A Comparative Analysis of Interpretable Machine Learning Methods

  Mattia Billa, Giovanni Orlandi, Veronica Guidetti, Federica Mandreoli · 5 janvier 2026

  In recent years, Machine Learning (ML) has seen widespread adoption across a broad range of sectors, including high-stakes domains such as healthcare, finance, and law. This growing reliance has raised increasing concerns regarding model interpretability and accountability, particularly as legal and…

• The Illusion of Insight in Reasoning Models

  Liv G. d'Aliberti, Manoel Horta Ribeiro · 5 janvier 2026

  Do reasoning models have "Aha!" moments? Prior work suggests that models like DeepSeek-R1-Zero undergo sudden mid-trace realizations that lead to accurate outputs, implying an intrinsic capacity for self-correction. Yet, it remains unclear whether such intrinsic shifts in reasoning strategy actually…

• Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations

  Qianli Wang, Nils Feldhus, Pepa Atanasova, Fedor Splitt, Simon Ostermann, Sebastian M\"oller, Vera Schmitt · 5 janvier 2026

  Quantization is widely used to accelerate inference and streamline the deployment of large language models (LLMs), yet its effects on self-explanations (SEs) remain unexplored. SEs, generated by LLMs to justify their own outputs, require reasoning about the model's own decision-making process, a cap…

• Interpretability-Guided Bi-objective Optimization: Aligning Accuracy and Explainability

  Kasra Fouladi, Hamta Rahmani · 5 janvier 2026

  This paper introduces Interpretability-Guided Bi-objective Optimization (IGBO), a framework that trains interpretable models by incorporating structured domain knowledge via a bi-objective formulation. IGBO encodes feature importance hierarchies as a Directed Acyclic Graph (DAG) and uses Temporal In…

• When Small Models Are Right for Wrong Reasons: Process Verification for Trustworthy Agents

  Laksh Advani · 5 janvier 2026

  Deploying small language models (7-9B parameters) as autonomous agents requires trust in their reasoning, not just their outputs. We reveal a critical reliability crisis: 50-69\% of correct answers from these models contain fundamentally flawed reasoning -- a ``Right-for-Wrong-Reasons'' phenomenon i…

• Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space

  Xingwei Qu, Shaowen Wang, Zihao Huang, Kai Hua, Fan Yin, Rui-Jie Zhu, Jundong Zhou, Qiyang Min, Zihao Wang, Yizhi Li, Tianyu Zhang, He Xing, Zheng Zhang, Yuxuan Song, Tianyu Zheng, Zhiyuan Zeng, Chenghua Lin, Ge Zhang, Wenhao Huang · 1 janvier 2026

  Large Language Models (LLMs) apply uniform computation to all tokens, despite language exhibiting highly non-uniform information density. This token-uniform regime wastes capacity on locally predictable spans while under-allocating computation to semantically critical transitions. We propose $\textb…

• Discovery and inference beyond linearity by integrating Bayesian regression, tree ensembles and Shapley values

  Giorgio Spadaccini, Marjolein Fokkema, Mark A. van de Wiel · 1 janvier 2026

  Machine Learning (ML) is gaining popularity for hypothesis-free discovery of risk and protective factors in healthcare studies. ML is strong at discovering nonlinearities and interactions, but this power is compromised by a lack of reliable inference. Although Shapley values provide local measures o…

• Iterative Deployment Improves Planning Skills in LLMs

  Augusto B. Corr\^ea, Yoav Gelberg, Luckeciano C. Melo, Ilia Shumailov, Andr\'e G. Pereira, Yarin Gal · 1 janvier 2026

  We show that iterative deployment of large language models (LLMs), each fine-tuned on data carefully curated by users from the previous models' deployment, can significantly change the properties of the resultant models. By testing this mechanism on various planning domains, we observe substantial i…

• Towards mechanistic understanding in a data-driven weather model: internal activations reveal interpretable physical features

  Theodore MacMillan, Nicholas T. Ouellette · 1 janvier 2026

  Large data-driven physics models like DeepMind's weather model GraphCast have empirically succeeded in parameterizing time operators for complex dynamical systems with an accuracy reaching or in some cases exceeding that of traditional physics-based solvers. Unfortunately, how these data-driven mode…

• Are Ensembles Getting Better all the Time?

  Pierre-Alexandre Mattei, Damien Garreau · 1 janvier 2026

  Ensemble methods combine the predictions of several base models. We study whether or not including more models always improves their average performance. This question depends on the kind of ensemble considered, as well as the predictive metric chosen. We focus on situations where all members of the…

• CogRec: A Cognitive Recommender Agent Fusing Large Language Models and Soar for Explainable Recommendation

  Jiaxin Hu, Tao Wang, Bingsan Yang, Hongrun Wang · 1 janvier 2026

  Large Language Models (LLMs) have demonstrated a remarkable capacity in understanding user preferences for recommendation systems. However, they are constrained by several critical challenges, including their inherent "Black-Box" characteristics, susceptibility to knowledge hallucination, and limite…

• Trustworthy Machine Learning under Distribution Shifts

  Zhuo Huang · 30 décembre 2025

  Machine Learning (ML) has been a foundational topic in artificial intelligence (AI), providing both theoretical groundwork and practical tools for its exciting advancements. From ResNet for visual recognition to Transformer for vision-language alignment, the AI models have achieved superior capabili…

• Feature Responsiveness Scores: Model-Agnostic Explanations for Recourse

  Harry Cheon, Anneke Wernerfelt, Sorelle A. Friedler, Berk Ustun · 30 décembre 2025

  Consumer protection rules require companies that deploy models to automate decisions in high-stakes settings to explain predictions to decision subjects. These rules are motivated, in part, by the belief that explanations can promote recourse by revealing information that decision subjects can use t…

• EvoXplain: When Machine Learning Models Agree on Predictions but Disagree on Why -- Measuring Mechanistic Multiplicity Across Training Runs

  Chama Bensmail · 30 décembre 2025

  Machine learning models are primarily judged by predictive performance, especially in applied settings. Once a model reaches high accuracy, its explanation is often assumed to be correct and trustworthy. However, this assumption raises an overlooked question: when two models achieve high accuracy, d…

• Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation

  Bhaktipriya Radharapu, Eshika Saxena, Kenneth Li, Chenxi Whitehouse, Adina Williams, Nicola Cancedda · 30 décembre 2025

  As LLM-based judges become integral to industry applications, obtaining well-calibrated uncertainty estimates efficiently has become critical for production deployment. However, existing techniques, such as verbalized confidence and multi-generation methods, are often either poorly calibrated or com…

• Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization

  Kerem Zaman, Shashank Srivastava · 30 décembre 2025

  Recent work, using the Biasing Features metric, labels a CoT as unfaithful if it omits a prompt-injected hint that affected the prediction. We argue this metric confuses unfaithfulness with incompleteness, the lossy compression needed to turn distributed transformer computation into a linear natural…

• Mechanistic Analysis of Circuit Preservation in Federated Learning

  Muhammad Haseeb, Salaar Masood, Muhammad Abdullah Sohail · 30 décembre 2025

  Federated Learning (FL) enables collaborative training of models on decentralized data, but its performance degrades significantly under Non-IID (non-independent and identically distributed) data conditions. While this accuracy loss is well-documented, the internal mechanistic causes remain a black …

• Towards Responsible and Explainable AI Agents with Consensus-Driven Reasoning

  Eranga Bandara, Tharaka Hewa, Ross Gore, Sachin Shetty, Ravi Mukkamala, Peter Foytik, Abdul Rahman, Safdar H. Bouk, Xueping Liang, Amin Hass, Sachini Rajapakse, Ng Wee Keong, Kasun De Zoysa, Aruna Withanage, Nilaan Loganathan · 29 décembre 2025

  Agentic AI represents a major shift in how autonomous systems reason, plan, and execute multi-step tasks through the coordination of Large Language Models (LLMs), Vision Language Models (VLMs), tools, and external services. While these systems enable powerful new capabilities, increasing autonomy in…

• Morality is Contextual: Learning Interpretable Moral Contexts from Human Data with Probabilistic Clustering and Large Language Models

  Geoffroy Morlat, Marceau Nahon, Augustin Chartouny, Raja Chatila, Ismael T. Freire, Mehdi Khamassi · 29 décembre 2025

  Moral actions are judged not only by their outcomes but by the context in which they occur. We present COMETH (Contextual Organization of Moral Evaluation from Textual Human inputs), a framework that integrates a probabilistic context learner with LLM-based semantic abstraction and human moral evalu…

• A Model of Causal Explanation on Neural Networks for Tabular Data

  Takashi Isozaki, Masahiro Yamamoto, Atsushi Noda · 29 décembre 2025

  The problem of explaining the results produced by machine learning methods continues to attract attention. Neural network (NN) models, along with gradient boosting machines, are expected to be utilized even in tabular data with high prediction accuracy. This study addresses the related issues of pse…

• A Causal Lens for Evaluating Faithfulness Metrics

  Kerem Zaman, Shashank Srivastava · 29 décembre 2025

  Large Language Models (LLMs) offer natural language explanations as an alternative to feature attribution methods for model interpretability. However, despite their plausibility, they may not reflect the model's true reasoning faithfully. While several faithfulness metrics have been proposed, they a…

• Inducing Causal World Models in LLMs for Zero-Shot Physical Reasoning

  Aditya Sharma, Ananya Gupta, Chengyu Wang, Chiamaka Adebayo, Jakub Kowalski · 29 décembre 2025

  Large Language Models (LLMs), despite their advanced linguistic capabilities, fundamentally lack an intuitive understanding of physical dynamics, which limits their effectiveness in real-world scenarios that require causal reasoning. In this paper, we introduce Causal World Model Induction (CWMI), a…