Explainable Artificial Intelligence (XAI)

Derniers papiers

• Hierarchical, Interpretable, Label-Free Concept Bottleneck Model

  Haodong Xie, Yujun Cai, Rahul Singh Maharjan, Yiwei Wang, Federico Tavella, Angelo Cangelosi · 6 avril 2026

  Concept Bottleneck Models (CBMs) introduce interpretability to black-box deep learning models by predicting labels through human-understandable concepts. However, unlike humans, who identify objects at different levels of abstraction using both general and specific features, existing CBMs operate at…

• Resting Neurons, Active Insights: Robustify Activation Sparsity for Large Language Models

  Haotian Xu, Jiannan Yang, Tian Gao, Tsui-Wei Weng, Tengfei Ma · 6 avril 2026

  Activation sparsity offers a compelling route to accelerate large language model (LLM) inference by selectively suppressing hidden activations, yet existing approaches exhibit severe accuracy degradation at high sparsity. We show that this failure stems from representational instability: *activation…

• FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models

  Kehan Jiang, Haonan Dong, Zhaolu Kang, Zhengzhou Zhu, Guojie Song · 6 avril 2026

  Recent Large Reasoning Models (LRMs) like DeepSeek-R1 have demonstrated remarkable success in complex reasoning tasks, exhibiting human-like patterns in exploring multiple alternative solutions. Upon closer inspection, however, we uncover a surprising phenomenon: The First is The Best, where alterna…

• DeltaLogic: Minimal Premise Edits Reveal Belief-Revision Failures in Logical Reasoning Models

  Amit Dhanda · 6 avril 2026

  Reasoning benchmarks typically evaluate whether a model derives the correct answer from a fixed premise set, but they under-measure a closely related capability that matters in dynamic environments: belief revision under minimal evidence change. We introduce DeltaLogic, a benchmark transformation pr…

• Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers

  Hita Kambhamettu, Alyssa Hwang, Philippe Laban, Andrew Head · 6 avril 2026

  AI answer engines are a relatively new kind of information search tool: rather than returning a ranked list of documents, they generate an answer to a search question with inline citations to sources. But reading the cited sources is costly, and citation links themselves offer little guidance about …

• Do We Need Frontier Models to Verify Mathematical Proofs?

  Aaditya Naik, Guruprerana Shabadi, Rajeev Alur, Mayur Naik · 6 avril 2026

  Advances in training, post-training, and inference-time methods have enabled frontier reasoning models to win gold medals in math competitions and settle challenging open problems. Gaining trust in the responses of these models requires that natural language proofs be checked for errors. LLM judges …

• Reinforcement Learning from Human Feedback: A Statistical Perspective

  Pangpang Liu, Chengchun Shi, Will Wei Sun · 6 avril 2026

  Reinforcement learning from human feedback (RLHF) has emerged as a central framework for aligning large language models (LLMs) with human preferences. Despite its practical success, RLHF raises fundamental statistical questions because it relies on noisy, subjective, and often heterogeneous feedback…

• Regularizing Attention Scores with Bootstrapping

  Neo Christopher Chung, Maxim Laletin · 3 avril 2026

  Vision transformers (ViT) rely on attention mechanism to weigh input features, and therefore attention scores have naturally been considered as explanations for its decision-making process. However, attention scores are almost always non-zero, resulting in noisy and diffused attention maps and limit…

• AI-Mediated Explainable Regulation for Justice

  Thomas Hofweber, Andreas Sudmann, Evangelos Pournaras · 2 avril 2026

  Present practice of deciding on regulation faces numerous problems that make adopted regulations static, unexplained, unduly influenced by powerful interest groups, and stained with a perception of illegitimacy. These well-known problems with the regulatory process can lead to injustice and have sub…

• How Emotion Shapes the Behavior of LLMs and Agents: A Mechanistic Study

  Moran Sun, Tianlin Li, Yuwei Zheng, Zhenhong Zhou, Aishan Liu, Xianglong Liu, Yang Liu · 2 avril 2026

  Emotion plays an important role in human cognition and performance. Motivated by this, we investigate whether analogous emotional signals can shape the behavior of large language models (LLMs) and agents. Existing emotion-aware studies mainly treat emotion as a surface-level style factor or a percep…

• $\texttt{YC-Bench}$: Benchmarking AI Agents for Long-Term Planning and Consistent Execution

  Muyu He, Adit Jain, Anand Kumar, Vincent Tu, Soumyadeep Bakshi, Sachin Patro, Nazneen Rajani · 2 avril 2026

  As LLM agents tackle increasingly complex tasks, a critical question is whether they can maintain strategic coherence over long horizons: planning under uncertainty, learning from delayed feedback, and adapting when early mistakes compound. We introduce $\texttt{YC-Bench}$, a benchmark that evaluate…

• Explainable AI for Blind and Low-Vision Users: Navigating Trust, Modality, and Interpretability in the Agentic Era

  Abu Noman Md Sakib, Protik Dey, Zijie Zhang, Taslima Akter · 2 avril 2026

  Explainable Artificial Intelligence (XAI) is critical for ensuring trust and accountability, yet its development remains predominantly visual. For blind and low-vision (BLV) users, the lack of accessible explanations creates a fundamental barrier to the independent use of AI-driven assistive technol…

• Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models

  Ponhvoan Srey, Quang Minh Nguyen, Xiaobao Wu, Anh Tuan Luu · 2 avril 2026

  Uncertainty estimation (UE) aims to detect hallucinated outputs of large language models (LLMs) to improve their reliability. However, UE metrics often exhibit unstable performance across configurations, which significantly limits their applicability. In this work, we formalise this phenomenon as pr…

• One Panel Does Not Fit All: Case-Adaptive Multi-Agent Deliberation for Clinical Prediction

  Yuxing Lu, Yushuhong Lin, Jason Zhang · 2 avril 2026

  Large language models applied to clinical prediction exhibit case-level heterogeneity: simple cases yield consistent outputs, while complex cases produce divergent predictions under minor prompt changes. Existing single-agent strategies sample from one role-conditioned distribution, and multi-agent …

• Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agents

  Thanh Luong Tuan · 2 avril 2026

  Enterprise adoption of Large Language Models (LLMs) is constrained by hallucination, domain drift, and the inability to enforce regulatory compliance at the reasoning level. We present a neurosymbolic architecture implemented within the Foundation AgenticOS (FAOS) platform that addresses these limit…

• Reasoning-Driven Synthetic Data Generation and Evaluation

  Tim R. Davidson, Benoit Seguin, Enrico Bacis, Cesar Ilharco, Hamza Harkous · 1 avril 2026

  Although many AI applications of interest require specialized multi-modal models, relevant data to train such models is inherently scarce or inaccessible. Filling these gaps with human annotators is prohibitively expensive, error-prone, and time-consuming, leading model builders to increasingly cons…

• Measuring the metacognition of AI

  Richard Servajean, Philippe Servajean · 1 avril 2026

  A robust decision-making process must take into account uncertainty, especially when the choice involves inherent risks. Because artificial Intelligence (AI) systems are increasingly integrated into decision-making workflows, managing uncertainty relies more and more on the metacognitive capabilitie…

• Structural Compactness as a Complementary Criterion for Explanation Quality

  Mohammad Mahdi Mesgari, Jackie Ma, Wojciech Samek, Sebastian Lapuschkin, Leander Weber · 1 avril 2026

  In the evaluation of attribution quality, the quantitative assessment of explanation legibility is particularly difficult, as it is influenced by varying shapes and internal organization of attributions not captured by simple statistics. To address this issue, we introduce Minimum Spanning Tree Comp…

• Rigorous Explanations for Tree Ensembles

  Yacine Izza, Alexey Ignatiev, Xuanxiang Huang, Peter J. Stuckey, Joao Marques-Silva · 1 avril 2026

  Tree ensembles (TEs) find a multitude of practical applications. They represent one of the most general and accurate classes of machine learning methods. While they are typically quite concise in representation, their operation remains inscrutable to human decision makers. One solution to build trus…

• ShapE-GRPO: Shapley-Enhanced Reward Allocation for Multi-Candidate LLM Training

  Rui Ai, Yu Pan, David Simchi-Levi, Chonghuan Wang · 1 avril 2026

  In user-agent interaction scenarios such as recommendation, brainstorming, and code suggestion, Large Language Models (LLMs) often generate sets of candidate recommendations where the objective is to maximize the collective utility of the entire set rather than individual candidates independently. H…

• Learning to Generate Formally Verifiable Step-by-Step Logic Reasoning via Structured Formal Intermediaries

  Luoxin Chen, Yichi Zhou, Huishuai Zhang · 1 avril 2026

  Large language models (LLMs) have recently demonstrated impressive performance on complex, multi-step reasoning tasks, especially when post-trained with outcome-rewarded reinforcement learning Guo et al. 2025. However, it has been observed that outcome rewards often overlook flawed intermediate step…

• Distilling LLM Reasoning into Graph of Concept Predictors

  Ziyang Yu, Liang Zhao · 1 avril 2026

  Deploying Large Language Models (LLMs) for discriminative workloads is often limited by inference latency, compute, and API costs at scale. Active distillation reduces these costs by querying an LLM oracle to train compact discriminative students, but most pipelines distill only final labels, discar…

• Structured Intent as a Protocol-Like Communication Layer: Cross-Model Robustness, Framework Comparison, and the Weak-Model Compensation Effect

  Peng Gang · 1 avril 2026

  How reliably can structured intent representations preserve user goals across different AI models, languages, and prompting frameworks? Prior work showed that PPS (Prompt Protocol Specification), a 5W3H-based structured intent framework, improves goal alignment in Chinese and generalizes to English …

• Uncertainty Gating for Cost-Aware Explainable Artificial Intelligence

  Georgii Mikriukov, Gr\'egoire Montavon, Marina M. -C. H\"ohne · 1 avril 2026

  Post-hoc explanation methods are widely used to interpret black-box predictions, but their generation is often computationally expensive and their reliability is not guaranteed. We propose epistemic uncertainty as a low-cost proxy for explanation reliability: high epistemic uncertainty identifies re…

• Concept frustration: Aligning human concepts and machine representations

  Enrico Parisini, Christopher J. Soelistyo, Ahab Isaac, Alessandro Barp, Christopher R. S. Banerji · 1 avril 2026

  Aligning human-interpretable concepts with the internal representations learned by modern machine learning systems remains a central challenge for interpretable AI. We introduce a geometric framework for comparing supervised human concepts with unsupervised intermediate representations extracted fro…