Explainable Artificial Intelligence (XAI)

Derniers papiers

• Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models

  Junyao Yang, Chen Qian, Kun Wang, Linfeng Zhang, Quanshi Zhang, Yong Liu, Dongrui Liu · 25 mai 2026

  The advancement of Large Reasoning Models (LRMs) has catalyzed a paradigm shift from reactive ``fast thinking'' text generation to systematic, step-by-step ``slow thinking'' reasoning, unlocking state-of-the-art performance in complex mathematical and logical tasks. However, the field faces \textit{…

• MARS: Magnitude-Aware Rank Statistics

  Muhammad Rajabinasab, Afsaneh M. Nejad, Arthur Zimek · 25 mai 2026

  Comprehensive evaluation of machine learning models is the key to make sure that they perform as robustly and consistently as desired. In order to summarize the experimental results and pick a winner, Critical Difference (CD) diagrams are used. Standard CD diagrams rely on discrete ranks, discarding…

• Proxy-Based Approximation of Shapley and Banzhaf Interactions

  Santo M. A. R. Thies, Hubert Baniecki, R. Teal Witter, Eyke H\"ullermeier, Maximilian Muschalik, Fabian Fumagalli · 25 mai 2026

  Shapley and Banzhaf interactions capture the complex dynamics inherent in modern machine learning applications. However, current estimators for these higher-order interactions trade off between speed and accuracy. To overcome this limitation, we introduce ProxySHAP. ProxySHAP reconciles the high sam…

• Ceci n'est pas une explication: Evaluating Explanation Failures as Explainability Pitfalls in Language Learning Systems

  Ben Knight, Wm. Matthew Kennedy, Danielle Carvalho, Isaac Pattis, James Edgell · 25 mai 2026

  AI-powered language learning tools increasingly provide instant, personalised feedback to millions of learners worldwide. However, this feedback can fail in ways that are difficult for learners--and even teachers--to detect, potentially reinforcing misconceptions and eroding learning outcomes over e…

• Uncovering the Latent Potential of Deep Intermediate Representations

  Arnesh Batra, Arush Gumber, Aniket Khandelwal, Jashn Khemani, Anubha Gupta · 25 mai 2026

  Foundational Models pretrained on huge amount of data learn representations that evolve across depth, forming a hierarchy of embeddings with distinct semantic content and geometric structure. Contrary to the widespread practice of using only the final layer or shallow mixtures, we show that task-rel…

• Robots That Know What to Ask: Recovering Misaligned Rewards through Targeted Explanations

  Helena Merker, Nick Walker, Andreea Bobu · 25 mai 2026

  Learning reward functions from demonstrations assumes that demonstrations provide adequate supervision over all features -- or task-relevant aspects of behavior. In practice, demonstrations are often imperfect: humans may under-emphasize certain features due to cognitive load or physical difficulty,…

• Decoding the Critique Mechanism in Large Reasoning Models

  Hoang Phan, Quang H. Nguyen, Hung T. Q. Le, Xiusi Chen, Heng Ji, Khoa D. Doan · 25 mai 2026

  Large Reasoning Models (LRMs) exhibit backtracking and self-verification mechanisms that enable them to revise intermediate steps and reach correct solutions, yielding strong performance on complex logical benchmarks. We hypothesize that such behaviors are beneficial only when the model has sufficie…

• Decomposition-Based Modular Conformal Prediction for Two-Stage Modeling

  William Zhang, Saurabh Amin, Georgia Perakis · 25 mai 2026

  Conformal prediction offers finite-sample coverage guarantees under minimal assumptions. However, existing methods treat the entire modeling process as a black box, overlooking opportunities to exploit and understand modular structure. We introduce a conformal prediction framework for two-stage sequ…

• GENSTRAT: Toward a Science of Strategic Reasoning in Large Language Models

  Vartan Shadarevian, Kia Ghods, Alex Kenich, Anany Kotawala · 25 mai 2026

  Large language models (LLMs) are increasingly deployed as economic agents in marketplaces, auctions, and bidding settings. Anticipating their behavior in any specific deployment is hard. Existing strategic-reasoning benchmarks evaluate models on fixed canonical games. These benchmarks may saturate a…

• Convergence Without Understanding: When Language Models Agree on Representations but Disagree on Reasoning

  Muhammad Usama, Dong Eui Chang · 25 mai 2026

  Large language models trained under diverse objectives and architectures have been shown to develop increasingly similar internal representations, an observation formalized as the Platonic Representation Hypothesis. Whether this representational convergence extends to the reasoning processes that op…

• AI Evaluation Should Require Standardized Item-Level Data Releases

  Han Jiang, Susu Zhang, Dongyao Zhu, Yuzhuo Bai, Sang T. Truong, Xiaoyuan Yi, Sanmi Koyejo, Xing Xie, Ziang Xiao · 25 mai 2026

  This position paper argues that standardized item-level benchmark data should become the default infrastructure for AI evaluation. Current evaluations suffer from underspecified item selection, construct misalignment, and poor generalization. The root cause of these failures is a misplaced focus on …

• Human Decision-Making with Persuasive and Narrative LLM Explanations

  Laura R. Marusich, Mary Grace Kozuch Dhooghe, Jonathan Z. Bakdash, Murat Kantarcioglu · 25 mai 2026

  Large language models (LLMs) have the potential to aid and improve human decision-making in classification tasks, not only by providing fairly accurate predictions, but also in their ability to generate cogent narrative explanations of those predictions. Prior work has demonstrated that people gener…

• Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents

  Jiazheng Kang, Bowen Zhang, Zixin Song, Jiangwang Chen, Xiao Yang, Da Zhu, Guanjun Jiang · 25 mai 2026

  ReAct-style agents for search-intensive, multi-step reasoning tasks rely largely on their own internal judgment to decide what evidence to seek, which reasoning or action step to take next, and when to stop, often producing shallow, redundant, or poorly targeted trajectories. Prior work has explored…

• From Residuals to Reasons: LLM-Guided Mechanism Inference from Tabular Data

  Mohammad R. Rezaei, Rahul G. Krishnan · 25 mai 2026

  A persistent challenge in machine learning for scientific applications is jointly achieving prediction and understanding. Statistical models excel on structured data but operate as black boxes, while existing interpretability methods are largely inspective: they answer "which features matter?" but d…

• Every Component is a Lookup: Token Attribution and Composition from a Single Decomposition

  Po-Kai Chen, Niki van Stein, Aske Plaat · 25 mai 2026

  Mechanistic interpretability of transformers requires identifying not just which components matter but how they compose into the computational route that produced a prediction. Both attention and MLP follow a shared key-value template $\phi(S)U$. We exploit this structure to develop Unpack, a backwa…

• Toward Template-Free Explainability for Monte Carlo Tree Search

  Siqi Lu, Mirsaleh Bahavarnia, Hiba Baroud, Yixuan Zhang, Hemant Purohit, Ayan Mukhopadhyay · 22 mai 2026

  Probabilistic search algorithms, such as Monte Carlo Tree Search (MCTS), have proven very effective in solving sequential decision-making tasks under uncertainty. However, interpreting asymmetric search trees that incorporate bandit-based tree traversal and simulation-based value estimation is diffi…

• Epistemic Regret Minimization: Label-Free Causal Critique Beyond Outcome Reward

  Edward Y. Chang, Longling Geng · 22 mai 2026

  Large language models can answer causal questions correctly for the wrong reasons. Current RL methods reward \emph{what} a model concludes but ignore \emph{why}, reinforcing correlational shortcuts -- a failure we call \emph{Reward Entrenchment}. We introduce \emph{Epistemic Regret Minimization} (\e…

• SAM-Sode: Towards Faithful Explanations for Tiny Bacteria Detection

  Wanying Tan, Shuo Yan, Dazhi Huang, Yazheng Liu, Zili Shao, Rufeng Chen, Hechang Chen, Mude Shi, Tianxing Ji, Sihong Xie · 22 mai 2026

  Interpretability in object detection provides crucial confidence support for clinical auxiliary diagnosis. However, in tiny bacteria detection, traditional explanation methods often suffer from blurred foreground boundaries and diffuse feature attribution due to the extreme sparsity of target morpho…

• STAR-P\'olyaMath: Multi-Agent Reasoning under Persistent Meta-Strategic Supervision

  Jiaao Wu, Xian Zhang, Hanzhang Liu, Sophia Zhang, Fan Yang, Yinpeng Dong · 21 mai 2026

  Frontier AI models and multi-agent systems have led to significant improvements in mathematical reasoning. However, for problems requiring extended, long-horizon reasoning, existing systems continue to suffer from fundamental reliability issues: hallucination accumulation, memory fragmentation, and …

• Decision-Path Patterns as Tree Reliability Signals: Path-based Adaptive Weighting for Random Forest Classification

  Youngjoon Park · 21 mai 2026

  Random forests aggregate tree votes by simple majority, treating all trees as equally informative. We observe that the topological pattern along each tree's root-to-leaf decision path -- where and how often the dominant class label flips along it -- carries a signal of tree reliability that is explo…

• Markovian Circuit Tracing for Transformer State Dynamic

  Abdullah X · 21 mai 2026

  Many sequence computations are easier to study as movement through internal states than as isolated local circuits. We introduce Markovian Circuit Tracing (MCT), a diagnostic pipeline for testing whether transformer activations contain coarse state-transition structure. The benchmark uses synthetic …

• The General Theory of Localization Methods

  Congwei Song · 21 mai 2026

  This paper proposes a general machine learning framework called the localization method, which is fundamentally built on two core concepts: localization kernels and local means -- key components that underpin the self-attention mechanism. To establish a rigorous theoretical foundation, the framework…

• Comparing Explanations is Not Enough, Explain the Change: New Standards are Needed to Explain Behavioral Shifts in Large Language Models

  Martino Ciaperoni, Marzio Di Vece, Roberto Pellungrini, Luca Pappalardo, Fosca Giannotti, Francesco Giannini · 21 mai 2026

  Large-scale foundation models exhibit \emph{behavioral shifts} when subjected to interventions such as scaling, fine-tuning, reinforcement learning with human feedback, or in-context learning. Current explainability methods are structurally ill-suited to explain these shifts, because they either tre…

• Matryoshka Concept Bottleneck Models

  Ziye Chen, Hongbin Lin, Xinyue Xu, Jie Li, Lijie Hu · 21 mai 2026

  Concept Bottleneck Models (CBMs) have emerged as a prominent paradigm for interpretable deep learning, learning by grounding predictions in human-understandable concepts. However, their practical deployment is hindered by the high cost of test-time intervention, as correcting model errors typically …

• Cross-Paradigm Knowledge Distillation: A Comprehensive Study of Bidirectional Transfer Between Random Forests and Deep Neural Networks for Big Data Applications

  Mahdi Naser Moghadasi · 20 mai 2026

  The exponential growth of big data has intensified the need for efficient and interpretable machine learning models that can handle diverse data characteristics while maintaining computational efficiency. Knowledge distillation has primarily focused on neural network-to-neural network transfer, leav…