Explainable Artificial Intelligence (XAI)

Derniers papiers

• A Framework for Evaluating Faithfulness in Explainable AI for Machine Anomalous Sound Detection Using Frequency-Band Perturbation

  Alexander Buck, Georgina Cosma, Iain Phillips, Paul Conway, Patrick Baker · 28 janvier 2026

  Explainable AI (XAI) is commonly applied to anomalous sound detection (ASD) models to identify which time-frequency regions of an audio signal contribute to an anomaly decision. However, most audio explanations rely on qualitative inspection of saliency maps, leaving open the question of whether the…

• Statistical Inference for Explainable Boosting Machines

  Haimo Fang, Kevin Tan, Jonathan Pipping, Giles Hooker · 28 janvier 2026

  Explainable boosting machines (EBMs) are popular "glass-box" models that learn a set of univariate functions using boosting trees. These achieve explainability through visualizations of each feature's effect. However, unlike linear model coefficients, uncertainty quantification for the learned univa…

• RobustExplain: Evaluating Robustness of LLM-Based Explanation Agents for Recommendation

  Guilin Zhang, Kai Zhao, Jeffrey Friedman, Xu Chu · 28 janvier 2026

  Large Language Models (LLMs) are increasingly used to generate natural-language explanations in recommender systems, acting as explanation agents that reason over user behavior histories. While prior work has focused on explanation fluency and relevance under fixed inputs, the robustness of LLM-gene…

• Holistic Explainable AI (H-XAI): Extending Transparency Beyond Developers in AI-Driven Decision Making

  Kausik Lakkaraju, Siva Likitha Valluru, Biplav Srivastava · 28 janvier 2026

  As AI systems increasingly mediate decisions in domains such as credit scoring and financial forecasting, their lack of transparency and bias raises critical concerns for fairness and public trust. Existing explainable AI (XAI) approaches largely serve developers, focusing on model justification rat…

• NIMO: a Nonlinear Interpretable MOdel

  Shijian Xu, Marcello Massimo Negri, Volker Roth · 28 janvier 2026

  Deep learning has achieved remarkable success across many domains, but it has also created a growing demand for interpretability in model predictions. Although many explainable machine learning methods have been proposed, post-hoc explanations lack guaranteed fidelity and are sensitive to hyperparam…

• HELM: A Human-Centered Evaluation Framework for LLM-Powered Recommender Systems

  Sushant Mehta · 28 janvier 2026

  The integration of Large Language Models (LLMs) into recommendation systems has introduced unprecedented capabilities for natural language understanding, explanation generation, and conversational interactions. However, existing evaluation methodologies focus predominantly on traditional accuracy me…

• LLM-Generated Explanations Do Not Suffice for Ultra-Strong Machine Learning

  Lun Ai, Johannes Langer, Ute Schmid, Stephen Muggleton · 28 janvier 2026

  Ultra Strong Machine Learning (USML) refers to symbolic learning systems that not only improve their own performance but can also teach their acquired knowledge to quantifiably improve human performance. We introduce LENS (Logic Programming Explanation via Neural Summarisation), a neuro-symbolic fra…

• Explaining Synergistic Effects in Social Recommendations

  Yicong Li, Shan Jin, Qi Liu, Shuo Wang, Jiaying Liu, Shuo Yu, Qiang Zhang, Kuanjiu Zhou, Feng Xia · 27 janvier 2026

  In social recommenders, the inherent nonlinearity and opacity of synergistic effects across multiple social networks hinders users from understanding how diverse information is leveraged for recommendations, consequently diminishing explainability. However, existing explainers can only identify the …

• PolySHAP: Extending KernelSHAP with Interaction-Informed Polynomial Regression

  Fabian Fumagalli, R. Teal Witter, Christopher Musco · 27 janvier 2026

  Shapley values have emerged as a central game-theoretic tool in explainable AI (XAI). However, computing Shapley values exactly requires $2^d$ game evaluations for a model with $d$ features. Lundberg and Lee's KernelSHAP algorithm has emerged as a leading method for avoiding this exponential cost. K…

• GCFX: Generative Counterfactual Explanations for Deep Graph Models at the Model Level

  Jinlong Hu, Jiacheng Liu · 27 janvier 2026

  Deep graph learning models have demonstrated remarkable capabilities in processing graph-structured data and have been widely applied across various fields. However, their complex internal architectures and lack of transparency make it difficult to explain their decisions, resulting in opaque models…

• UniCog: Uncovering Cognitive Abilities of LLMs through Latent Mind Space Analysis

  Jiayu Liu, Yinhe Long, Zhenya Huang, Enhong Chen · 27 janvier 2026

  A growing body of research suggests that the cognitive processes of large language models (LLMs) differ fundamentally from those of humans. However, existing interpretability methods remain limited in explaining how cognitive abilities are engaged during LLM reasoning. In this paper, we propose UniC…

• Dynamic Thinking-Token Selection for Efficient Reasoning in Large Reasoning Models

  Zhenyuan Guo, Tong Chen, Wenlong Meng, Chen Gong, Xin Yu, Chengkun Wei, Wenzhi Chen · 27 janvier 2026

  Large Reasoning Models (LRMs) excel at solving complex problems by explicitly generating a reasoning trace before deriving the final answer. However, these extended generations incur substantial memory footprint and computational overhead, bottlenecking LRMs' efficiency. This work uses attention map…

• Interpretability of the Intent Detection Problem: A New Approach

  Eduardo Sanchez-Karhunen, Jose F. Quesada-Moreno, Miguel A. Guti\'errez-Naranjo · 27 janvier 2026

  Intent detection, a fundamental text classification task, aims to identify and label the semantics of user queries, playing a vital role in numerous business applications. Despite the dominance of deep learning techniques in this field, the internal mechanisms enabling Recurrent Neural Networks (RNN…

• Conformal Feedback Alignment: Quantifying Answer-Level Reliability for Robust LLM Alignment

  Tiejin Chen, Xiaoou Liu, Vishnu Nandam, Kuan-Ru Liou, Hua Wei · 27 janvier 2026

  Preference-based alignment like Reinforcement Learning from Human Feedback (RLHF) learns from pairwise preferences, yet the labels are often noisy and inconsistent. Existing uncertainty-aware approaches weight preferences, but ignore a more fundamental factor: the reliability of the \emph{answers} b…

• TruthTensor: Evaluating LLMs through Human Imitation on Prediction Market under Drift and Holistic Reasoning

  Shirin Shahabi, Spencer Graham, Haruna Isah · 27 janvier 2026

  Evaluating language models and AI agents remains fundamentally challenging because static benchmarks fail to capture real-world uncertainty, distribution shift, and the gap between isolated task accuracy and human-aligned decision-making under evolving conditions. This paper introduces TruthTensor, …

• Interpreting Agentic Systems: Beyond Model Explanations to System-Level Accountability

  Judy Zhu, Dhari Gandhi, Himanshu Joshi, Ahmad Rezaie Mianroodi, Sedef Akinli Kocak, Dhanesh Ramachandran · 27 janvier 2026

  Agentic systems have transformed how Large Language Models (LLMs) can be leveraged to create autonomous systems with goal-directed behaviors, consisting of multi-step planning and the ability to interact with different environments. These systems differ fundamentally from traditional machine learnin…

• Unifying VXAI: A Systematic Review and Framework for the Evaluation of Explainable AI

  David Dembinsky, Adriano Lucieri, Stanislav Frolov, Hiba Najjar, Ko Watanabe, Andreas Dengel · 27 janvier 2026

  Modern AI systems frequently rely on opaque black-box models, most notably Deep Neural Networks, whose performance stems from complex architectures with millions of learned parameters. While powerful, their complexity poses a major challenge to trustworthiness, particularly due to a lack of transpar…

• Scientifically-Interpretable Reasoning Network (ScIReN): Discovering Hidden Relationships in the Carbon Cycle and Beyond

  Joshua Fan, Haodi Xu, Feng Tao, Md Nasim, Marc Grimson, Yiqi Luo, Carla P. Gomes · 27 janvier 2026

  Soils have potential to mitigate climate change by sequestering carbon from the atmosphere, but the soil carbon cycle remains poorly understood. Scientists have developed process-based models of the soil carbon cycle based on existing knowledge, but they contain numerous unknown parameters and often…

• JaxARC: A High-Performance JAX-based Environment for Abstraction and Reasoning Research

  Aadam, Monu Verma, Mohamed Abdel-Mottaleb · 27 janvier 2026

  The Abstraction and Reasoning Corpus (ARC) tests AI systems' ability to perform human-like inductive reasoning from a few demonstration pairs. Existing Gymnasium-based RL environments severely limit experimental scale due to computational bottlenecks. We present JaxARC, an open-source, high-performa…

• GameTalk: Training LLMs for Strategic Conversation

  Victor Conchello Vendrell, Max Ruiz Luyten, Mihaela van der Schaar · 26 janvier 2026

  Strategic decision-making in multi-agent settings is a key challenge for large language models (LLMs), particularly when coordination and negotiation must unfold over extended conversations. While recent work has explored the use of LLMs in isolated decision tasks, little attention has been given to…

• Provably Robust Bayesian Counterfactual Explanations under Model Changes

  Jamie Duell, Xiuyi Fan · 26 janvier 2026

  Counterfactual explanations (CEs) offer interpretable insights into machine learning predictions by answering ``what if?" questions. However, in real-world settings where models are frequently updated, existing counterfactual explanations can quickly become invalid or unreliable. In this paper, we i…

• Jacobian Scopes: token-level causal attributions in LLMs

  Toni J. B. Liu, Baran Zadeo\u{g}lu, Nicolas Boull\'e, Rapha\"el Sarfati, Christopher J. Earls · 26 janvier 2026

  Large language models (LLMs) make next-token predictions based on clues present in their context, such as semantic descriptions and in-context examples. Yet, elucidating which prior tokens most strongly influence a given prediction remains challenging due to the proliferation of layers and attention…

• Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders

  Aaron J. Li, Suraj Srinivas, Usha Bhalla, Himabindu Lakkaraju · 26 janvier 2026

  Sparse autoencoders (SAEs) are commonly used to interpret the internal activations of large language models (LLMs) by mapping them to human-interpretable concept representations. While existing evaluations of SAEs focus on metrics such as the reconstruction-sparsity tradeoff, human (auto-)interpreta…

• Counterfactual Training: Teaching Models Plausible and Actionable Explanations

  Patrick Altmeyer, Aleksander Buszydlik, Arie van Deursen, Cynthia C. S. Liem · 23 janvier 2026

  We propose a novel training regime termed counterfactual training that leverages counterfactual explanations to increase the explanatory capacity of models. Counterfactual explanations have emerged as a popular post-hoc explanation method for opaque machine learning models: they inform how factual i…

• Explainable AI to Improve Machine Learning Reliability for Industrial Cyber-Physical Systems

  Annemarie Jutte, Uraz Odyurt · 23 janvier 2026

  Industrial Cyber-Physical Systems (CPS) are sensitive infrastructure from both safety and economics perspectives, making their reliability critically important. Machine Learning (ML), specifically deep learning, is increasingly integrated in industrial CPS, but the inherent complexity of ML models r…