Explainable Artificial Intelligence (XAI)

Derniers papiers

• LLM Psychosis: A Theoretical and Diagnostic Framework for Reality-Boundary Failures in Large Language Models

  Ashutosh Raj · 30 avril 2026

  The deployment of large language models (LLMs) as interactive agents has exposed a category of behavioral failure that prevailing terminology, principally hallucination, fails to adequately characterize. This paper introduces LLM Psychosis as a structured theoretical framework for pathological break…

• reward-lens: A Mechanistic Interpretability Library for Reward Models

  Mohammed Suhail B Nadaf · 30 avril 2026

  Every RLHF-trained language model is shaped by a reward model, yet the mechanistic interpretability toolkit -- logit lens, direct logit attribution, activation patching, sparse autoencoders -- was built for generative LLMs whose primitives all project onto a vocabulary unembedding. Reward models rep…

• Ceci n'est pas une explication: Evaluating Explanation Failures as Explainability Pitfalls in Language Learning Systems

  Ben Knight, Wm. Matthew Kennedy, James Edgell · 30 avril 2026

  AI-powered language learning tools increasingly provide instant, personalised feedback to millions of learners worldwide. However, this feedback can fail in ways that are difficult for learners--and even teachers--to detect, potentially reinforcing misconceptions and eroding learning outcomes over e…

• Explainable Representation of Finite-Memory Policies for POMDPs using Decision Trees

  Muqsit Azeem, Debraj Chakraborty, Sudeep Kanav, Jan Kretinsky · 30 avril 2026

  Partially Observable Markov Decision Processes (POMDPs) are a fundamental framework for decision-making under uncertainty and partial observability. Since in general optimal policies may require infinite memory, they are hard to implement and often render most problems undecidable. Consequently, fin…

• Tree-of-Evidence: Efficient "System 2" Search for Faithful Multimodal Grounding

  Micky C. Nnamdi, Benoit L. Marteau, Yishan Zhong, J. Ben Tamo, May D. Wang · 30 avril 2026

  Large Multimodal Models (LMMs) achieve state-of-the-art performance in high-stakes domains like healthcare, yet their reasoning remains opaque. Current interpretability methods, such as attention mechanisms or post-hoc saliency, often fail to faithfully represent the model's decision-making process,…

• Auto-Relational Reasoning

  Ioannis Konstantoulas, Dimosthenis Tsimas, Pavlos Peppas, Kyriakos Sgarbas · 30 avril 2026

  Background & Objectives: In the last decade, Machine learning research has grown rapidly, but large models are reaching their soft limits demonstrating diminishing returns and still lack solid reasoning abilities. These limits could be surpassed through synergistic combination of Machine Learning sc…

• Incompressible Knowledge Probes: Estimating Black-Box LLM Parameter Counts via Factual Capacity

  Bojie Li · 29 avril 2026

  Closed-source frontier labs do not disclose parameter counts, and the standard alternative -- inference economics -- carries $2\times$+ uncertainty from hardware, batching, and serving-stack assumptions external to the model. We exploit a tighter intrinsic bound: storing $F$ facts requires at least …

• RCProb: Probabilistic Rule Extraction for Efficient Simplification of Tree Ensembles

  Josue Obregon · 29 avril 2026

  Tree ensembles are widely used in industrial machine learning due to their strong predictive performance and efficient training procedures. However, as the number of trees in an ensemble grows, the resulting models become increasingly difficult for humans to interpret. To address this limitation, ex…

• Towards interpretable AI with quantum annealing feature selection

  Francesco Aldo Venturelli, Emanuele Costa, Sikha O K, Bruno Juli\'a-D\'iaz, Miguel A. Gonz\'alez Ballester, Alba Cervera-Lierta · 29 avril 2026

  Deep learning models are used in critical applications, in which mistakes can have serious consequences. Therefore, it is crucial to understand how and why models generate predictions. This understanding provides useful information to check whether the model is learning the right patterns, detect bi…

• Explanation Quality Assessment as Ranking with Listwise Rewards

  Thomas Bailleux, Tanmoy Mukherjee, Emmanuel Lonca, Pierre Marquis, Zied Bouraoui · 29 avril 2026

  We reformulate explanation quality assessment as a ranking problem rather than a generation problem. Instead of optimizing models to produce a single "best" explanation token-by-token, we train reward models to discriminate among multiple candidate explanations and learn their relative quality. Conc…

• IndustryAssetEQA: A Neurosymbolic Operational Intelligence System for Embodied Question Answering in Industrial Asset Maintenance

  Chathurangi Shyalika, Dhaval Patel, Amit Sheth · 29 avril 2026

  Industrial maintenance environments increasingly rely on AI systems to assist operators in understanding asset behavior, diagnosing failures, and evaluating interventions. Although large language models (LLMs) enable fluent natural-language interaction, deployed maintenance assistants routinely prod…

• Domain-Filtered Knowledge Graphs from Sparse Autoencoder Features

  John Winnicki, Abeynaya Gnanasekaran, Eric Darve · 29 avril 2026

  Sparse autoencoders (SAEs) extract millions of interpretable features from a language model, but flat feature inventories aren't very useful on their own. Domain concepts get mixed with generic and weakly grounded features, while related ideas are scattered across many units, and there's no way to u…

• GSAR: Typed Grounding for Hallucination Detection and Recovery in Multi-Agent LLMs

  Federico A. Kamelhar · 29 avril 2026

  Autonomous multi-agent LLM systems are increasingly deployed to investigate operational incidents and produce structured diagnostic reports. Their trustworthiness hinges on whether each claim is grounded in observed evidence rather than model-internal inference. Existing groundedness evaluators (bin…

• Applications of the Transformer Architecture in AI-Assisted English Reading Comprehension

  Ping Li · 29 avril 2026

  This paper studies interpretable and fair artificial intelligence architectures for understanding English reading. Introduced transformer-based models, integrating advanced attention mechanisms and gradient-based feature attribution. The model's lack of interpretability, reduction of algorithmic bia…

• Explainable AI in Speaker Recognition -- Making Latent Representations Understandable

  Yanze Xu, Wenwu Wang, Mark D. Plumbley · 29 avril 2026

  Neural networks can be trained to learn task-relevant representations from data. Understanding how these networks make decisions falls within the Explainable AI (XAI) domain. This paper proposes to study an XAI topic: uncovering unknown organisational patterns in network representations, particularl…

• Negative Ontology of True Target for Machine Learning: Towards Evaluation and Learning under Democratic Supervision

  Yongquan Yang · 29 avril 2026

  This article philosophically examines how shifts in assumptions regarding the existence and non-existence of the true target (TT) give rise to new perspectives and insights for machine learning (ML)-based predictive modeling and, correspondingly, proposes a knowledge system for evaluation and learni…

• DenoGrad: A Gradient-Based Framework for Data Refinement in Tabular and Time-Series Learning

  J. Javier Alonso-Ramos, Ignacio Aguilera-Martos, Francisco Herrera, Andr\'es Herrera-Poyatos · 28 avril 2026

  In the Data-Centric Artificial Intelligence (AI) paradigm, improving data quality is essential for robust machine learning. However, many denoising methods rely on rigid statistical assumptions or require clean reference data, which limits their applicability in real-world scenarios. In this work, w…

• MetaErr: Towards Predicting Error Patterns in Deep Neural Networks

  Varun Totakura, Shayok Chakraborty · 28 avril 2026

  Due to the unprecedented success of deep learning, it has become an integral component in several multimedia computing applications in todays world. Unfortunately, deep learning systems are not perfect and can fail, sometimes abruptly, without prior warning or explanation. While reducing the error r…

• Explaining Temporal Graph Predictions With Shapley Values

  Lea-Marie Sussek, Stefan Heindorf · 28 avril 2026

  Temporal Graph Neural Networks (TGNNs) have become increasingly popular in recent years due to their superior predictive performance by combining both spatial and temporal information. However, how these models utilize the information to make predictions is rather unexplored, leading to potentially …

• XGRAG: A Graph-Native Framework for Explaining KG-based Retrieval-Augmented Generation

  Zhuoling Li, Ha Linh Hong Tran Nguyen, Valeria Bladinieres, Maxim Romanovsky · 28 avril 2026

  Graph-based Retrieval-Augmented Generation (GraphRAG) extends traditional RAG by using knowledge graphs (KGs) to give large language models (LLMs) a structured, semantically coherent context, yielding more grounded answers. However, GraphRAG reasoning process remains a black-box, limiting our abilit…

• CoFi-PGMA: Counterfactual Policy Gradients under Filtered Feedback for Multi-Agent LLMs

  Stela Tong, Elai Ben-Gal · 28 avril 2026

  Large language model (LLM) deployments increasingly rely on multi-agent architectures in which multiple models either compete through routing mechanisms or collaborate to produce a final answer. In both settings, the learning signal received by each agent is filtered by the system mechanism. Routing…

• Hindsight Preference Optimization for Financial Time Series Advisory

  Yanwei Cui, Guanghui Wang, Xing Zhang, Peiyang He, Ziyuan Li, Bing Zhu, Wei Qiu, Xusheng Wang, Zheng Yu, Anqi Xin · 28 avril 2026

  Time series models predict numbers; decision-makers need advisory -- directional signals with reasoning, actionable suggestions, and risk management. Training language models for such predictive advisory faces a fundamental challenge: quality depends on outcomes unknown at prediction time. We bridge…

• Differentiable Filtering for Learning Hidden Markov Models

  Reginald Zhiyan Chen, Heng-Sheng Chang, Prashant G. Mehta · 27 avril 2026

  Hidden Markov Models (HMMs) are fundamental for modeling sequential data, yet learning their parameters from observations remains challenging. Classical methods like the Baum-Welch algorithm are computationally intensive and prone to local optima, while modern spectral algorithms offer provable guar…

• Algorithmic Feature Highlighting for Human-AI Decision-Making

  Yifan Guo, Jann Spiess · 27 avril 2026

  Human decision-makers often face choices about complex cases with many potentially relevant features, but limited bandwidth to inspect and integrate all available information. In such settings, we study algorithms that highlight a small subset of case-specific features for human consideration, rathe…

• Explanation of Dynamic Physical Field Predictions using WassersteinGrad: Application to Autoregressive Weather Forecasting

  Younes Essafouri, Laure Raynaud, Luciano Drozda, Laurent Risser · 27 avril 2026

  As the demand to integrate Artificial Intelligence into high-stakes environments continues to grow, explaining the reasoning behind neural-network predictions has shifted from a theoretical curiosity to a strict operational requirement. Our work is motivated by the explanations of autoregressive neu…