Explainable Artificial Intelligence (XAI)

Derniers papiers

• From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents

  Trilok Padhi, Ramneet Kaur, Krishiv Agarwal, Adam D. Cobb, Daniel Elenius, Manoj Acharya, Colin Samplawski, Alexander M. Berenbeim, Nathaniel D. Bastian, Susmit Jha, Anirban Roy · 24 avril 2026

  Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of reasoning, planning, and acting within interactive environments. Despite their growing capability to perform multi-step reasoning and decision-making tasks, internal mechanisms guiding their sequential behavior re…

• Using Learning Theories to Evolve Human-Centered XAI: Future Perspectives and Challenges

  Karina Cortinas-Lorenzo, Gavin Doherty · 24 avril 2026

  As Artificial Intelligence (AI) systems continue to grow in size and complexity, so does the difficulty of the quest for AI transparency. In a world of large models and complex AI systems, why do we explain AI and what should we explain? While explanations serve multiple functions, in the face of co…

• Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs

  Moein Salimi, Shaygan Adim, Danial Parnian, Nima Alighardashi, Mahdi Jafari Siavoshani, Mohammad Hossein Rohban · 24 avril 2026

  Regardless of its foundational role in human discovery and sense-making, abductive reasoning--the inference of the most plausible explanation for an observation--has been relatively underexplored in Large Language Models (LLMs). Despite the rapid advancement of LLMs, the exploration of abductive rea…

• Learning When Not to Decide: A Framework for Overcoming Factual Presumptuousness in AI Adjudication

  Mohamed Afane, Emily Robitschek, Derek Ouyang, Daniel E. Ho · 24 avril 2026

  A well-known limitation of AI systems is presumptuousness: the tendency of AI systems to provide confident answers when information may be lacking. This challenge is particularly acute in legal applications, where a core task for attorneys, judges, and administrators is to determine whether evidence…

• Mechanistic Decoding of Cognitive Constructs in Large Language Models

  Yitong Shou, Manhao Guan · 24 avril 2026

  While Large Language Models (LLMs) demonstrate increasingly sophisticated affective capabilities, the internal mechanisms by which they process complex emotions remain unclear. Existing interpretability approaches often treat models as black boxes or focus on coarse-grained basic emotions, leaving t…

• Stateless Decision Memory for Enterprise AI Agents

  Vasundra Srinivasan · 24 avril 2026

  Enterprise deployment of long-horizon decision agents in regulated domains (underwriting, claims adjudication, tax examination) is dominated by retrieval-augmented pipelines despite a decade of increasingly sophisticated stateful memory architectures. We argue this reflects a hidden requirement: reg…

• ActuBench: A Multi-Agent LLM Pipeline for Generation and Evaluation of Actuarial Reasoning Tasks

  Jan-Philipp Schmidt · 24 avril 2026

  We present ActuBench, a multi-agent LLM pipeline for the automated generation and evaluation of advanced actuarial assessment items aligned with the International Actuarial Association (IAA) Education Syllabus. The pipeline separates four LLM roles by adapter: one agent drafts items, one constructs …

• Not-a-Bandit: Provably No-Regret Drafter Selection in Speculative Decoding for LLMs

  Hongyi Liu, Jiaji Huang, Zhen Jia, Youngsuk Park, Yu-Xiang Wang · 24 avril 2026

  Speculative decoding is widely used in accelerating large language model (LLM) inference. In this work, we focus on the online draft model selection problem in speculative decoding. We design an algorithm that provably competes with the best draft model in hindsight for each query in terms of either…

• Cross-Entropy Is Load-Bearing: A Pre-Registered Scope Test of the K-Way Energy Probe on Bidirectional Predictive Coding

  Jon-Paul Cacioli · 24 avril 2026

  Cacioli (2026) showed that the K-way energy probe on standard discriminative predictive coding networks reduces approximately to a monotone function of the log-softmax margin. The reduction rests on five assumptions, including cross-entropy (CE) at the output and effectively feedforward inference dy…

• LayerTracer: A Joint Task-Particle and Vulnerable-Layer Analysis framework for Arbitrary Large Language Model Architectures

  Yuhang Wu, Qinyuan Liu, Qiuyang Zhao, Qingwei Chong · 24 avril 2026

  Currently, Large Language Models (LLMs) feature a diversified architectural landscape, including traditional Transformer, GateDeltaNet, and Mamba. However, the evolutionary laws of hierarchical representations, task knowledge formation positions, and network robustness bottleneck mechanisms in vario…

• TriEx: A Game-based Tri-View Framework for Explaining Internal Reasoning in Multi-Agent LLMs

  Ziyi Wang, Chen Zhang, Wenjun Peng, Qi Wu, Xinyu Wang · 24 avril 2026

  Explainability for Large Language Model (LLM) agents is especially challenging in interactive, partially observable settings, where decisions depend on evolving beliefs and other agents. We present \textbf{TriEx}, a tri-view explainability framework that instruments sequential decision making with a…

• IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory

  Weitong Kong, Di Wen, Kunyu Peng, David Schneider, Zeyun Zhong, Alexander Jaus, Zdravko Marinov, Jiale Wei, Ruiping Liu, Junwei Zheng, Yufan Chen, Lei Qi, Rainer Stiefelhagen · 24 avril 2026

  Correcting errors in long-video understanding is disproportionately costly: existing multimodal pipelines produce opaque, end-to-end outputs that expose no intermediate state for inspection, forcing annotators to revisit raw video and reconstruct temporal logic from scratch. The core bottleneck is n…

• Improving Performance in Classification Tasks with LCEN and the Weighted Focal Differentiable MCC Loss

  Pedro Seber, Richard D. Braatz · 24 avril 2026

  The LASSO-Clip-EN (LCEN) algorithm was previously introduced for nonlinear, interpretable feature selection and machine learning. However, its design and use was limited to regression tasks. In this work, we create a modified version of the LCEN algorithm that is suitable for classification tasks an…

• Context Attribution with Multi-Armed Bandit Optimization

  Deng Pan, Keerthiram Murugesan, Ting Hua, Nuno Moniz, Nitesh Chawla · 24 avril 2026

  Understanding which parts of the retrieved context contribute to a large language model's generated answer is essential for building interpretable and trustworthy retrieval-augmented generation. We propose a novel framework that formulates context attribution as a combinatorial multi-armed bandit pr…

• LAF-Based Evaluation and UTTL-Based Learning Strategies with MIATTs

  Yongquan Yang · 24 avril 2026

  In many real-world machine learning (ML) applications, the true target cannot be precisely defined due to ambiguity or subjectivity information. To address this challenge, under the assumption that the true target for a given ML task is not assumed to exist objectively in the real world, the EL-MIAT…

• Interpretable Quantile Regression by Optimal Decision Trees

  Valentin Lemaire, Ga\"el Aglin, Siegfried Nijssen · 24 avril 2026

  The field of machine learning is subject to an increasing interest in models that are not only accurate but also interpretable and robust, thus allowing their end users to understand and trust AI systems. This paper presents a novel method for learning a set of optimal quantile regression trees. The…

• Deep FinResearch Bench: Evaluating AI's Ability to Conduct Professional Financial Investment Research

  Mirazul Haque, Antony Papadimitriou, Samuel Mensah, Zhiqiang Ma, Zhijin Guo, Joy Prakash Sain, Simerjot Kaur, Charese Smiley, Xiaomo Liu · 24 avril 2026

  We introduce Deep FinResearch Bench, a practical and comprehensive evaluation framework for deep research (DR) agents in financial investment research. The benchmark assesses three dimensions of report quality: qualitative rigor, quantitative forecasting and valuation accuracy, and claim credibility…

• Large Language Models Outperform Humans in Fraud Detection and Resistance to Motivated Investor Pressure

  Nattavudh Powdthavee · 24 avril 2026

  Large language models trained on human feedback may suppress fraud warnings when investors arrive already persuaded of a fraudulent opportunity. We tested this in a preregistered experiment across seven leading LLMs and twelve investment scenarios covering legitimate, high-risk, and objectively frau…

• MIRROR: A Hierarchical Benchmark for Metacognitive Calibration in Large Language Models

  Jason Z Wang · 23 avril 2026

  We introduce MIRROR, a benchmark comprising eight experiments across four metacognitive levels that evaluates whether large language models can use self-knowledge to make better decisions. We evaluate 16 models from 8 labs across approximately 250,000 evaluation instances using five independent beha…

• Differentiable Conformal Training for LLM Reasoning Factuality

  Nathan Hittesdorf, Marco Salzetta, Lu Cheng · 23 avril 2026

  Large Language Models (LLMs) frequently hallucinate, limiting their reliability in critical applications. Conformal Prediction (CP) addresses this by calibrating error rates on held-out data to provide statistically valid confidence guarantees. Recent work extends CP to LLM factuality to filter out …

• MGDA-Decoupled: Geometry-Aware Multi-Objective Optimisation for DPO-based LLM Alignment

  Andor V\'ari-Kakas, Ji Won Park, Natasa Tagasovska · 23 avril 2026

  Aligning large language models (LLMs) to desirable human values requires balancing multiple, potentially conflicting objectives such as helpfulness, truthfulness, and harmlessness, which presents a multi-objective optimisation challenge. Most alignment pipelines rely on a fixed scalarisation of thes…

• Mechanistic Interpretability Tool for AI Weather Models

  Kirsten I. Tempest, Matthias Beylich, George C. Craig · 23 avril 2026

  Artificial Intelligence (AI) weather models are improving rapidly, and their forecasts are already competitive with long-established traditional Numerical Weather Prediction (NWP). To build confidence in this new methodology, it is critical that we understand how these predictions are generated. Thi…

• Accumulated Aggregated D-Optimal Designs for Estimating Main Effects in Black-Box Models

  Chih-Yu Chang, Ming-Chung Chang · 23 avril 2026

  Estimating how individual input variables affect the output of a black-box model is a central task in explainable machine learning. However, existing methods suffer from two key limitations: sensitivity to out-of-distribution (OOD) evaluations, which arises when query points are placed far from the …

• On the definition and importance of interpretability in scientific machine learning

  Conor Rowan, Alireza Doostan · 23 avril 2026

  Though neural networks trained on large datasets have been successfully used to describe and predict many physical phenomena, there is a sense among scientists that, unlike traditional scientific models comprising simple mathematical expressions, their findings cannot be integrated into the body of …

• Concept Graph Convolutions: Message Passing in the Concept Space

  Lucie Charlotte Magister, Pietro Lio · 23 avril 2026

  The trust in the predictions of Graph Neural Networks is limited by their opaque reasoning process. Prior methods have tried to explain graph networks via concept-based explanations extracted from the latent representations obtained after message passing. However, these explanations fall short of ex…