Explainable Artificial Intelligence (XAI)

Derniers papiers

• A Logical-Rule Autoencoder for Interpretable Recommendations

  Jinhao Pan, Bowen Wei, Ziwei Zhu · 7 avril 2026

  Most deep learning recommendation models operate as black boxes, relying on latent representations that obscure their decision process. This lack of intrinsic interpretability raises concerns in applications that require transparency and accountability. In this work, we propose a Logical-rule Interp…

• From Hallucination to Scheming: A Unified Taxonomy and Benchmark Analysis for LLM Deception

  Jerick Shi, Terry Jingcheng Zhang, Zhijing Jin, Vincent Conitzer · 7 avril 2026

  Large language models (LLMs) produce systematically misleading outputs, from hallucinated citations to strategic deception of evaluators, yet these phenomena are studied by separate communities with incompatible terminology. We propose a unified taxonomy organized along three complementary dimension…

• Early Stopping for Large Reasoning Models via Confidence Dynamics

  Parsa Hosseini, Sumit Nawathe, Mahdi Salmani, Meisam Razaviyayn, Soheil Feizi · 7 avril 2026

  Large reasoning models rely on long chain-of-thought generation to solve complex problems, but extended reasoning often incurs substantial computational cost and can even degrade performance due to overthinking. A key challenge is determining when the model should stop reasoning and produce the fina…

• Are Latent Reasoning Models Easily Interpretable?

  Connor Dilgren, Sarah Wiegreffe · 7 avril 2026

  Latent reasoning models (LRMs) have attracted significant research interest due to their low inference cost (relative to explicit reasoning models) and theoretical ability to explore multiple reasoning paths in parallel. However, these benefits come at the cost of reduced interpretability: LRMs are …

• Selecting Decision-Relevant Concepts in Reinforcement Learning

  Naveen Raman, Stephanie Milani, Fei Fang · 7 avril 2026

  Training interpretable concept-based policies requires practitioners to manually select which human-understandable concepts an agent should reason with when making sequential decisions. This selection demands domain expertise, is time-consuming and costly, scales poorly with the number of candidates…

• AdaptFuse: Training-Free Sequential Preference Learning via Externalized Bayesian Inference

  Fangzhou Lin, Peiran Li, Shuo Xing, Siyuan Yang, Qianwen Ge, Kazunori Yamada, Ziming Zhang, Haichong Zhang, Zhengzhong Tu · 7 avril 2026

  Large language models struggle to accumulate evidence across multiple rounds of user interaction, failing to update their beliefs in a manner consistent with Bayesian inference. Existing solutions require fine-tuning on sensitive user interaction data, limiting their applicability in privacy-conscio…

• Selective Forgetting for Large Reasoning Models

  Tuan Le, Wei Qian, Mengdi Huai · 7 avril 2026

  Large Reasoning Models (LRMs) generate structured chains of thought (CoTs) before producing final answers, making them especially vulnerable to knowledge leakage through intermediate reasoning steps. Yet, the memorization of sensitive information in the training data such as copyrighted and private …

• Rethinking Exploration in RLVR: From Entropy Regularization to Refinement via Bidirectional Entropy Modulation

  Hengrui Gu, Xiaotian Han, Yujing Bian, Kaixiong Zhou · 7 avril 2026

  Reinforcement learning with verifiable rewards (RLVR) has significantly advanced the reasoning capabilities of large language models (LLMs). However, it faces a fundamental limitation termed \textit{restricted exploration}, where the policy rapidly converges to a narrow set of solutions. While entro…

• ArrowFlow: Hierarchical Machine Learning in the Space of Permutations

  Ozgur Yilmaz · 7 avril 2026

  We introduce ArrowFlow, a machine learning architecture that operates entirely in the space of permutations. Its computational units are ranking filters, learned orderings that compare inputs via Spearman's footrule distance and update through permutation-matrix accumulation, a non-gradient rule roo…

• Learning An Interpretable Risk Scoring System for Maximizing Decision Net Benefit

  Wenhao Chi, \c{S}. \.Ilker Birbil · 7 avril 2026

  Risk scoring systems are widely used in high-stakes domains to assist decision-making. However, existing approaches often focus on optimizing predictive accuracy or likelihood-based criteria, which may not align with the main goal of maximizing utility. In this paper, we propose a novel risk scoring…

• Automated Attention Pattern Discovery at Scale in Large Language Models

  Jonathan Katzy, Razvan-Mihai Popescu, Erik Mekkes, Arie van Deursen, Maliheh Izadi · 7 avril 2026

  Large language models have found success by scaling up capabilities to work in general settings. The same can unfortunately not be said for interpretability methods. The current trend in mechanistic interpretability is to provide precise explanations of specific behaviors in controlled settings. The…

• Evolutionary Search for Automated Design of Uncertainty Quantification Methods

  Mikhail Seleznyov, Daniil Korbut, Viktor Moskvoretskii, Oleg Somov, Alexander Panchenko, Elena Tutubalina · 7 avril 2026

  Uncertainty quantification (UQ) methods for large language models are predominantly designed by hand based on domain knowledge and heuristics, limiting their scalability and generality. We apply LLM-powered evolutionary search to automatically discover unsupervised UQ methods represented as Python p…

• xRFM: Accurate, scalable, and interpretable feature learning models for tabular data

  Daniel Beaglehole, David Holzm\"uller, Adityanarayanan Radhakrishnan, Mikhail Belkin · 7 avril 2026

  Inference from tabular data, collections of continuous and categorical variables organized into matrices, is a foundation for modern technology and science. Yet, in contrast to the explosive changes in the rest of AI, the best practice for these predictive tasks has been relatively unchanged and is …

• Reproducibility study on how to find Spurious Correlations, Shortcut Learning, Clever Hans or Group-Distributional non-robustness and how to fix them

  Ole Delzer, Sidney Bender · 7 avril 2026

  Deep Neural Networks (DNNs) are increasingly utilized in high-stakes domains like medical diagnostics and autonomous driving where model reliability is critical. However, the research landscape for ensuring this reliability is terminologically fractured across communities that pursue the same goal o…

• Position: Science of AI Evaluation Requires Item-level Benchmark Data

  Han Jiang, Susu Zhang, Xiaoyuan Yi, Xing Xie, Ziang Xiao · 7 avril 2026

  AI evaluations have become the primary evidence for deploying generative AI systems across high-stakes domains. However, current evaluation paradigms often exhibit systemic validity failures. These issues, ranging from unjustified design choices to misaligned metrics, remain intractable without a pr…

• Effects of Generative AI Errors on User Reliance Across Task Difficulty

  Jacy Reese Anthis, Hannah Cha, Solon Barocas, Alexandra Chouldechova, Jake Hofman · 7 avril 2026

  The capabilities of artificial intelligence (AI) lie along a jagged frontier, where AI systems surprisingly fail on tasks that humans find easy and succeed on tasks that humans find hard. To investigate user reactions to this phenomenon, we developed an incentive-compatible experimental methodology …

• GUIDE: Interpretable GUI Agent Evaluation via Hierarchical Diagnosis

  Yuwen Zhai, Runze Li, Liang Wang, Nian Shi, Liwu Xu, Wei Zhang, Ran Lin, Bo Xu, Benlei Cui · 7 avril 2026

  Evaluating GUI agents presents a distinct challenge: trajectories are long, visually grounded, and open-ended, yet evaluation must be both accurate and interpretable. Existing approaches typically apply a single holistic judgment over the entire action-observation sequence-a strategy that proves unr…

• Empirical Characterization of Rationale Stability Under Controlled Perturbations for Explainable Pattern Recognition

  Abu Noman Md Sakib, Zhensen Wang, Merjulah Roby, Zijie Zhang · 7 avril 2026

  Reliable pattern recognition systems should exhibit consistent behavior across similar inputs, and their explanations should remain stable. However, most Explainable AI evaluations remain instance centric and do not explicitly quantify whether attribution patterns are consistent across samples that …

• Making Bias Non-Predictive: Training Robust LLM Reasoning via Reinforcement Learning

  Qian Wang, Xuandong Zhao, Zirui Zhang, Zhanzhi Lou, Nuo Chen, Dawn Song, Bingsheng He · 7 avril 2026

  Large language models (LLMs) increasingly serve as reasoners and automated evaluators, yet they remain susceptible to cognitive biases -- often altering their reasoning when faced with spurious prompt-level cues such as consensus claims or authority appeals.} Existing mitigations via prompting or su…

• Implementing surrogate goals for safer bargaining in LLM-based agents

  Caspar Oesterheld, Maxime Rich\'e, Filip Sondej, Jesse Clifton, Vincent Conitzer · 7 avril 2026

  Surrogate goals have been proposed as a strategy for reducing risks from bargaining failures. A surrogate goal is goal that a principal can give an AI agent and that deflects any threats against the agent away from what the principal cares about. For example, one might make one's agent care about pr…

• Cheap Talk, Empty Promise: Frontier LLMs easily break public promises for self-interest

  Jerick Shi, Terry Jingcheng Zhang, Zhijing Jin, Vincent Conitzer · 7 avril 2026

  Large language models are increasingly deployed as autonomous agents in multi-agent settings where they communicate intentions and take consequential actions with limited human oversight. A critical safety question is whether agents that publicly commit to actions break those promises when they can …

• Quantifying Trust: Financial Risk Management for Trustworthy AI Agents

  Wenyue Hua, Tianyi Peng, Chi Wang, Ian Kaufman, Bryan Lim, Chandler Fang · 7 avril 2026

  Prior work on trustworthy AI emphasizes model-internal properties such as bias mitigation, adversarial robustness, and interpretability. As AI systems evolve into autonomous agents deployed in open environments and increasingly connected to payments or assets, the operational meaning of trust shifts…

• Posterior-Calibrated Causal Circuits in Variational Autoencoders: Why Image-Domain Interpretability Fails on Tabular Data

  Dip Roy, Rajiv Misra, Sanjay Kumar Singh, Anisha Roy · 7 avril 2026

  Although mechanism-based interpretability has generated an abundance of insight for discriminative network analysis, generative models are less understood -- particularly outside of image-related applications. We investigate how much of the causal circuitry found within image-related variational aut…

• The Persuasion Paradox: When LLM Explanations Fail to Improve Human-AI Team Performance

  Ruth Cohen, Lu Feng, Ayala Bloch, Sarit Kraus · 7 avril 2026

  While natural-language explanations from large language models (LLMs) are widely adopted to improve transparency and trust, their impact on objective human-AI team performance remains poorly understood. We identify a Persuasion Paradox: fluent explanations systematically increase user confidence and…

• A Model of Understanding in Deep Learning Systems

  David Peter Wallis Freeborn · 7 avril 2026

  I propose a model of systematic understanding, suitable for machine learning systems. On this account, an agent understands a property of a target system when it contains an adequate internal model that tracks real regularities, is coupled to the target by stable bridge principles, and supports reli…