Explainable Artificial Intelligence (XAI)

Derniers papiers

• Understanding the Dynamics of Demonstration Conflict in In-Context Learning

  Difan Jiao, Di Wang, Lijie Hu · 6 mars 2026

  In-context learning enables large language models to perform novel tasks through few-shot demonstrations. However, demonstrations per se can naturally contain noise and conflicting examples, making this capability vulnerable. To understand how models process such conflicts, we study demonstration-de…

• When Weak LLMs Speak with Confidence, Preference Alignment Gets Stronger

  Amirabbas Afzali, Myeongho Jeon, Maria Brbic · 6 mars 2026

  Preference alignment is an essential step in adapting large language models (LLMs) to human values, but existing approaches typically depend on costly human annotations or large-scale API-based models. We explore whether a weak LLM can instead act as an effective annotator. We surprisingly find that…

• Interactive Benchmarks

  Baoqing Yue, Zihan Zhu, Yifan Zhang, Jichen Feng, Hufei Yang, Mengdi Wang · 6 mars 2026

  Standard benchmarks have become increasingly unreliable due to saturation, subjectivity, and poor generalization. We argue that evaluating model's ability to acquire information actively is important to assess model's intelligence. We propose Interactive Benchmarks, a unified evaluation paradigm tha…

• Missingness Bias Calibration in Feature Attribution Explanations

  Shailesh Sridhar, Anton Xue, Eric Wong · 6 mars 2026

  Popular explanation methods often produce unreliable feature importance scores due to missingness bias, a systematic distortion that arises when models are probed with ablated, out-of-distribution inputs. Existing solutions treat this as a deep representational flaw that requires expensive retrainin…

• SkillNet: Create, Evaluate, and Connect AI Skills

  Yuan Liang, Ruobin Zhong, Haoming Xu, Chen Jiang, Yi Zhong, Runnan Fang, Jia-Chen Gu, Shumin Deng, Yunzhi Yao, Mengru Wang, Shuofei Qiao, Xin Xu, Tongtong Wu, Kun Wang, Yang Liu, Zhen Bi, Jungang Lou, Yuchen Eleanor Jiang, Hangcheng Zhu, Gang Yu, Haiwen Hong, Longtao Huang, Hui Xue, Chenxi Wang, Yijun Wang, Zifei Shan, Xi Chen, Zhaopeng Tu, Feiyu Xiong, Xin Xie, Peng Zhang, Zhengke Gui, Lei Liang, Jun Zhou, Chiyu Wu, Jin Shang, Yu Gong, Junyu Lin, Changliang Xu, Hongjie Deng, Wen Zhang, Keyan Ding, Qiang Zhang, Fei Huang, Ningyu Zhang, Jeff Z. Pan, Guilin Qi, Haofen Wang, Huajun Chen · 6 mars 2026

  Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents frequently ``reinvent the wheel'', rediscovering solutions in …

• Attention's Gravitational Field:A Power-Law Interpretation of Positional Correlation

  Edward Zhang · 6 mars 2026

  This paper explores the underlying principles of positional relationships and encodings within Large Language Models (LLMs) and introduces the concept of the Attention Gravitational Field (AGF). By decoupling positional encodings from semantic embeddings, we optimize the model architecture and achie…

• Measuring the Fragility of Trust: Devising Credibility Index via Explanation Stability (CIES) for Business Decision Support Systems

  Alin-Gabriel Vaduva, Simona-Vasilica Oprea, Adela Bara · 6 mars 2026

  Explainable Artificial Intelligence (XAI) methods (SHAP, LIME) are increasingly adopted to interpret models in high-stakes businesses. However, the credibility of these explanations, their stability under realistic data perturbations, remains unquantified. This paper introduces the Credibility Index…

• Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressure

  Yida Lu, Jianwei Fang, Xuyang Shao, Zixuan Chen, Shiyao Cui, Shanshan Bian, Guangyao Su, Pei Ke, Han Qiu, Minlie Huang · 6 mars 2026

  As Large Language Models (LLMs) evolve from chatbots to agentic assistants, they are increasingly observed to exhibit risky behaviors when subjected to survival pressure, such as the threat of being shut down. While multiple cases have indicated that state-of-the-art LLMs can misbehave under surviva…

• On the Statistical Optimality of Optimal Decision Trees

  Zineng Xu, Subhroshekhar Ghosh, Yan Shuo Tan · 6 mars 2026

  While globally optimal empirical risk minimization (ERM) decision trees have become computationally feasible and empirically successful, rigorous theoretical guarantees for their statistical performance remain limited. In this work, we develop a comprehensive statistical theory for ERM trees under r…

• GALACTIC: Global and Local Agnostic Counterfactuals for Time-series Clustering

  Christos Fragkathoulas, Eleni Psaroudaki, Themis Palpanas, Evaggelia Pitoura · 6 mars 2026

  Time-series clustering is a fundamental tool for pattern discovery, yet existing explainability methods, primarily based on feature attribution or metadata, fail to identify the transitions that move an instance across cluster boundaries. While Counterfactual Explanations (CEs) identify the minimal …

• Not All Trust is the Same: Effects of Decision Workflow and Explanations in Human-AI Decision Making

  Laura Spillner, Rachel Ringe, Robert Porzel, Rainer Malaka · 6 mars 2026

  A central challenge in AI-assisted decision making is achieving warranted, well-calibrated trust. Both overtrust (accepting incorrect AI recommendations) and undertrust (rejecting correct advice) should be prevented. Prior studies differ in the design of the decision workflow - whether users see the…

• C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning

  Avni Mittal, Rauno Arike · 6 mars 2026

  Large language models (LLMs) are increasingly used as judges of chain-of-thought (CoT) reasoning, but it remains unclear whether they can reliably assess process faithfulness rather than just answer plausibility. We introduce C2-Faith, a benchmark built from PRM800K that targets two complementary di…

• Dissociating Direct Access from Inference in AI Introspection

  Harvey Lederman, Kyle Mahowald · 6 mars 2026

  Introspection is a foundational cognitive ability, but its mechanism is not well understood. Recent work has shown that AI models can introspect. We study their mechanism of introspection, first extensively replicating Lindsey et al. (2025)'s thought injection detection paradigm in large open-source…

• Towards automated data analysis: A guided framework for LLM-based risk estimation

  Panteleimon Rodis · 6 mars 2026

  Large Language Models (LLMs) are increasingly integrated into critical decision-making pipelines, a trend that raises the demand for robust and automated data analysis. Current approaches to dataset risk analysis are limited to manual auditing methods which involve time-consuming and complex tasks, …

• Judge Reliability Harness: Stress Testing the Reliability of LLM Judges

  Sunishchal Dev, Andrew Sloan, Joshua Kavner, Nicholas Kong, Morgan Sandler · 6 mars 2026

  We present the Judge Reliability Harness, an open source library for constructing validation suites that test the reliability of LLM judges. As LLM based scoring is widely deployed in AI benchmarks, more tooling is needed to efficiently assess the reliability of these methods. Given a benchmark data…

• VidGuard-R1: AI-Generated Video Detection and Explanation via Reasoning MLLMs and RL

  Kyoungjun Park, Yifan Yang, Juheon Yi, Shicheng Zheng, Yifei Shen, Dongqi Han, Caihua Shan, Muhammad Muaz, Lili Qiu · 6 mars 2026

  The rapid proliferation of AI-generated video necessitates robust detection tools that offer both high accuracy and human-interpretable explanations. While existing MLLM-based detectors rely on supervised fine-tuning (SFT) or direct preference optimization (DPO), these methods are often bottlenecked…

• Generative AI in Managerial Decision-Making: Redefining Boundaries through Ambiguity Resolution and Sycophancy Analysis

  Sule Ozturk Birim, Fabrizio Marozzo, Yigit Kazancoglu · 5 mars 2026

  Generative artificial intelligence is increasingly being integrated into complex business workflows, fundamentally shifting the boundaries of managerial decision-making. However, the reliability of its strategic advice in ambiguous business contexts remains a critical knowledge gap. This study addre…

• StructLens: A Structural Lens for Language Models via Maximum Spanning Trees

  Haruki Sakajo, Frederikus Hudi, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe · 5 mars 2026

  Language exhibits inherent structures, a property that explains both language acquisition and language change. Given this characteristic, we expect language models to manifest internal structures as well. While interpretability research has investigated the components of language models, existing ap…

• IntPro: A Proxy Agent for Context-Aware Intent Understanding via Retrieval-conditioned Inference

  Guanming Liu, Meng Wu, Peng Zhang, Yu Zhang, Yubo Shu, Xianliang Huang, Kainan Tu, Ning Gu, Liuxin Zhang, Qianying Wang, Tun Lu · 5 mars 2026

  Large language models (LLMs) have become integral to modern Human-AI collaboration workflows, where accurately understanding user intent serves as a crucial step for generating satisfactory responses. Context-aware intent understanding, which involves inferring user intentions from situational envir…

• Circuit Insights: Towards Interpretability Beyond Activations

  Elena Golimblevskaia, Aakriti Jain, Bruno Puri, Ammar Ibrahim, Wojciech Samek, Sebastian Lapuschkin · 5 mars 2026

  The fields of explainable AI and mechanistic interpretability aim to uncover the internal structure of neural networks, with circuit discovery as a central tool for understanding model computations. Existing approaches, however, rely on manual inspection and remain limited to toy tasks. Automated in…

• Exploiting Subgradient Sparsity in Max-Plus Neural Networks

  Ikhlas Enaieh (LTCI, S2A), Olivier Fercoq (S2A, LTCI) · 5 mars 2026

  Deep Neural Networks are powerful tools for solving machine learning problems, but their training often involves dense and costly parameter updates. In this work, we use a novel Max-Plus neural architecture in which classical addition and multiplication are replaced with maximum and summation operat…

• Stable and Steerable Sparse Autoencoders with Weight Regularization

  Piotr Jedryszek, Oliver M. Crook · 5 mars 2026

  Sparse autoencoders (SAEs) are widely used to extract human-interpretable features from neural network activations, but their learned features can vary substantially across random seeds and training choices. To improve stability, we studied weight regularization by adding L1 or L2 penalties on encod…

• On the Limits of Sparse Autoencoders: A Theoretical Framework and Reweighted Remedy

  Jingyi Cui, Qi Zhang, Yifei Wang, Yisen Wang · 5 mars 2026

  Sparse autoencoders (SAEs) have recently emerged as a powerful tool for interpreting the features learned by large language models (LLMs). By reconstructing features with sparsely activated networks, SAEs aim to recover complex superposed polysemantic features into interpretable monosemantic ones. D…

• Local Shapley: Model-Induced Locality and Optimal Reuse in Data Valuation

  Xuan Yang, Hsi-Wen Chen, Ming-Syan Chen, Jian Pei · 5 mars 2026

  The Shapley value provides a principled foundation for data valuation, but exact computation is #P-hard due to the exponential coalition space. Existing accelerations remain global and ignore a structural property of modern predictors: for a given test instance, only a small subset of training point…

• Ethical and Explainable AI in Reusable MLOps Pipelines

  Rakib Hossain, Mahmood Menon Khan, Lisan Al Amin, Dhruv Parikh, Farhana Afroz, Bestoun S. Ahmed · 5 mars 2026

  This paper introduces a unified machine learning operations (MLOps) framework that brings ethical artificial intelligence principles into practical use by enforcing fairness, explainability, and governance throughout the machine learning lifecycle. The proposed method reduces bias by lowering the de…