Explainable Artificial Intelligence (XAI)

Derniers papiers

• XChoice: Explainable Evaluation of AI-Human Alignment in LLM-based Constrained Choice Decision Making

  Weihong Qi, Fan Huang, Rasika Muralidharan, Jisun An, Haewoon Kwak · 19 janvier 2026

  We present XChoice, an explainable framework for evaluating AI-human alignment in constrained decision making. Moving beyond outcome agreement such as accuracy and F1 score, XChoice fits a mechanism-based decision model to human data and LLM-generated decisions, recovering interpretable parameters t…

• Explaining Time Series Classifiers with PHAR: Rule Extraction and Fusion from Post-hoc Attributions

  Maciej Mozolewski, Szymon Bobek, Grzegorz J. Nalepa · 19 janvier 2026

  Explaining machine learning (ML) models for time series (TS) classification remains challenging due to the difficulty of interpreting raw time series and the high dimensionality of the input space. We introduce PHAR--Post-hoc Attribution Rules--a unified framework that transforms numeric feature att…

• Combating Spurious Correlations in Graph Interpretability via Self-Reflection

  Kecheng Cai, Chenyang Xu, Chao Peng · 19 janvier 2026

  Interpretable graph learning has recently emerged as a popular research topic in machine learning. The goal is to identify the important nodes and edges of an input graph that are crucial for performing a specific graph reasoning task. A number of studies have been conducted in this area, and variou…

• Beyond Model Scaling: Test-Time Intervention for Efficient Deep Reasoning

  Qianyue Wang, Jinwu Hu, Yufeng Wang, Huanxiang Lin, Bolin Chen, Zhiquan Wen, Yaofo Chen, Mingkui Tan · 19 janvier 2026

  Large Reasoning Models (LRMs) excel at multi-step reasoning but often suffer from inefficient reasoning processes like overthinking and overshoot, where excessive or misdirected reasoning increases computational cost and degrades performance. Existing efficient reasoning methods operate in a closed-…

• How DDAIR you? Disambiguated Data Augmentation for Intent Recognition

  Galo Castillo-L\'opez, Alexis Lombard, Nasredine Semmar, Ga\"el de Chalendar · 19 janvier 2026

  Large Language Models (LLMs) are effective for data augmentation in classification tasks like intent detection. In some cases, they inadvertently produce examples that are ambiguous with regard to untargeted classes. We present DDAIR (Disambiguated Data Augmentation for Intent Recognition) to mitiga…

• TimeSAE: Sparse Decoding for Faithful Explanations of Black-Box Time Series Models

  Khalid Oublal, Quentin Bouniot, Qi Gan, Stephan Cl\'emen\c{c}on, Zeynep Akata · 16 janvier 2026

  As black box models and pretrained models gain traction in time series applications, understanding and explaining their predictions becomes increasingly vital, especially in high-stakes domains where interpretability and trust are essential. However, most of the existing methods involve only in-dist…

• LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals

  Gilat Toker, Nitay Calderon, Ohad Amosy, Roi Reichart · 16 janvier 2026

  Concept-based explanations quantify how high-level concepts (e.g., gender or experience) influence model behavior, which is crucial for decision-makers in high-stakes domains. Recent work evaluates the faithfulness of such explanations by comparing them to reference causal effects estimated from cou…

• Are Your Reasoning Models Reasoning or Guessing? A Mechanistic Analysis of Hierarchical Reasoning Models

  Zirui Ren, Ziming Liu · 16 janvier 2026

  Hierarchical reasoning model (HRM) achieves extraordinary performance on various reasoning tasks, significantly outperforming large language model-based reasoners. To understand the strengths and potential failure modes of HRM, we conduct a mechanistic study on its reasoning patterns and find three …

• Breaking Up with Normatively Monolithic Agency with GRACE: A Reason-Based Neuro-Symbolic Architecture for Safe and Ethical AI Alignment

  Felix Jahn, Yannic Muskalla, Lisa Dargasz, Patrick Schramowski, Kevin Baum · 16 janvier 2026

  As AI agents become increasingly autonomous, widely deployed in consequential contexts, and efficacious in bringing about real-world impacts, ensuring that their decisions are not only instrumentally effective but also normatively aligned has become critical. We introduce a neuro-symbolic reason-bas…

• Hallucination Detection and Mitigation in Large Language Models

  Ahmad Pesaranghader, Erin Li · 16 janvier 2026

  Large Language Models (LLMs) and Large Reasoning Models (LRMs) offer transformative potential for high-stakes domains like finance and law, but their tendency to hallucinate, generating factually incorrect or unsupported content, poses a critical reliability risk. This paper introduces a comprehensi…

• Beyond Rule-Based Workflows: An Information-Flow-Orchestrated Multi-Agents Paradigm via Agent-to-Agent Communication from CORAL

  Xinxing Ren, Quagmire Zang, Caelum Forder, Suman Deb, Ahsen Tahir, Roman J. Georgio, Peter Carroll, Zekun Guo · 16 janvier 2026

  Most existing Large Language Model (LLM)-based Multi-Agent Systems (MAS) rely on predefined workflows, where human engineers enumerate task states in advance and specify routing rules and contextual injections accordingly. Such workflow-driven designs are essentially rule-based decision trees, which…

• Exploring specialization and sensitivity of convolutional neural networks in the context of simultaneous image augmentations

  Pavel Kharyuk, Sergey Matveev, Ivan Oseledets · 16 janvier 2026

  Drawing parallels with the way biological networks are studied, we adapt the treatment--control paradigm to explainable artificial intelligence research and enrich it through multi-parametric input alterations. In this study, we propose a framework for investigating the internal inference impacted b…

• Process-Guided Concept Bottleneck Model

  Reza M. Asiyabi (School of GeoSciences, University of Edinburgh, UK, UK National Centre for Earth Observation), SEOSAW Partnership (School of GeoSciences, University of Edinburgh, UK), Steven Hancock (School of GeoSciences, University of Edinburgh, UK, UK National Centre for Earth Observation), Casey Ryan (School of GeoSciences, University of Edinburgh, UK) · 16 janvier 2026

  Concept Bottleneck Models (CBMs) improve the explainability of black-box Deep Learning (DL) by introducing intermediate semantic concepts. However, standard CBMs often overlook domain-specific relationships and causal mechanisms, and their dependence on complete concept labels limits applicability i…

• DecisionLLM: Large Language Models for Long Sequence Decision Exploration

  Xiaowei Lv, Zhilin Zhang, Yijun Li, Yusen Huo, Siyuan Ju, Xuyan Li, Chunxiang Hong, Tianyu Wang, Yongcai Wang, Peng Sun, Chuan Yu, Jian Xu, Bo Zheng · 16 janvier 2026

  Long-sequence decision-making, which is usually addressed through reinforcement learning (RL), is a critical component for optimizing strategic operations in dynamic environments, such as real-time bidding in computational advertising. The Decision Transformer (DT) introduced a powerful paradigm by …

• Thinking Long, but Short: Stable Sequential Test-Time Scaling for Large Reasoning Models

  Michael R. Metel, Yufei Cui, Boxing Chen, Prasanna Parthasarathi · 16 janvier 2026

  Sequential test-time scaling is a promising training-free method to improve large reasoning model accuracy, but as currently implemented, significant limitations have been observed. Inducing models to think for longer can increase their accuracy, but as the length of reasoning is further extended, i…

• Syntactic Framing Fragility: An Audit of Robustness in LLM Ethical Decisions

  Katherine Elkins, Jon Chun · 16 janvier 2026

  Large language models (LLMs) are increasingly deployed in consequential decision-making settings, yet their robustness to benign prompt variation remains underexplored. In this work, we study whether LLMs maintain consistent ethical judgments across logically equivalent but syntactically different p…

• In-Context Learning Enhanced Credibility Transformer

  Kishan Padayachy, Ronald Richman, Salvatore Scognamiglio, Mario V. W\"uthrich · 15 janvier 2026

  The starting point of our network architecture is the Credibility Transformer which extends the classical Transformer architecture by a credibility mechanism to improve model learning and predictive performance. This Credibility Transformer learns credibilitized CLS tokens that serve as learned repr…

• Toward Understanding Unlearning Difficulty: A Mechanistic Perspective and Circuit-Guided Difficulty Metric

  Jiali Cheng, Ziheng Chen, Chirag Agarwal, Hadi Amiri · 15 janvier 2026

  Machine unlearning is becoming essential for building trustworthy and compliant language models. Yet unlearning success varies considerably across individual samples: some are reliably erased, while others persist despite the same procedure. We argue that this disparity is not only a data-side pheno…

• Interpretable Probability Estimation with LLMs via Shapley Reconstruction

  Yang Nan, Qihao Wen, Jiahao Wang, Pengfei He, Ravi Tandon, Yong Ge, Han Xu · 15 janvier 2026

  Large Language Models (LLMs) demonstrate potential to estimate the probability of uncertain events, by leveraging their extensive knowledge and reasoning capabilities. This ability can be applied to support intelligent decision-making across diverse fields, such as financial forecasting and preventi…

• On the Hardness of Computing Counterfactual and Semifactual Explanations in XAI

  Andr\'e Artelt, Martin Olsen, Kevin Tierney · 15 janvier 2026

  Providing clear explanations to the choices of machine learning models is essential for these models to be deployed in crucial applications. Counterfactual and semi-factual explanations have emerged as two mechanisms for providing users with insights into the outputs of their models. We provide an o…

• A Beautiful Mind: Principles and Strategies for AI-Augmented Human Reasoning

  Sean Koon · 15 janvier 2026

  Amidst the race to create more intelligent machines there is a risk that we will rely on AI in ways that reduce our own agency as humans. To reduce this risk, we could aim to create tools that prioritize and enhance the human role in human-AI interactions. This paper outlines a human-centered augmen…

• Resolving Predictive Multiplicity for the Rashomon Set

  Parian Haghighat, Hadis Anahideh, Cynthia Rudin · 15 janvier 2026

  The existence of multiple, equally accurate models for a given predictive task leads to predictive multiplicity, where a ``Rashomon set'' of models achieve similar accuracy but diverges in their individual predictions. This inconsistency undermines trust in high-stakes applications where we want con…

• ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning

  Ruiyang Zhou, Shuozhe Li, Amy Zhang, Liu Leqi · 15 janvier 2026

  Self-improvement via RL often fails on complex reasoning tasks because GRPO-style post-training methods rely on the model's initial ability to generate positive samples. Without guided exploration, these approaches merely reinforce what the model already knows (distribution-sharpening) rather than e…

• Attention Consistency Regularization for Interpretable Early-Exit Neural Networks

  Yanhua Zhao · 15 janvier 2026

  Early-exit neural networks enable adaptive inference by allowing predictions at intermediate layers, reducing computational cost. However, early exits often lack interpretability and may focus on different features than deeper layers, limiting trust and explainability. This paper presents Explanatio…

• Where Knowledge Collides: A Mechanistic Study of Intra-Memory Knowledge Conflict in Language Models

  Minh Vu Pham, Hsuvas Borkakoty, Yufang Hou · 15 janvier 2026

  In language models (LMs), intra-memory knowledge conflict largely arises when inconsistent information about the same event is encoded within the model's parametric knowledge. While prior work has primarily focused on resolving conflicts between a model's internal knowledge and external resources th…