Explainable Artificial Intelligence (XAI)

Derniers papiers

• Agentic Explainable Artificial Intelligence (Agentic XAI) Approach To Explore Better Explanation

  Tomoaki Yamaguchi, Yutong Zhou, Masahiro Ryo, Keisuke Katsura · 25 décembre 2025

  Explainable artificial intelligence (XAI) enables data-driven understanding of factor associations with response variables, yet communicating XAI outputs to laypersons remains challenging, hindering trust in AI-based predictions. Large language models (LLMs) have emerged as promising tools for trans…

• Uncovering Competency Gaps in Large Language Models and Their Benchmarks

  Matyas Bohacek, Nino Scherrer, Nicholas Dufour, Thomas Leung, Christoph Bregler, Stephanie C. Y. Chan · 25 décembre 2025

  The evaluation of large language models (LLMs) relies heavily on standardized benchmarks. These benchmarks provide useful aggregated metrics for a given capability, but those aggregated metrics can obscure (i) particular sub-areas where the LLMs are weak ("model gaps") and (ii) imbalanced coverage i…

• Can Agentic AI Match the Performance of Human Data Scientists?

  An Luo, Jin Du, Fangqiao Tian, Xun Xian, Robert Specht, Ganghua Wang, Xuan Bi, Charles Fleming, Jayanth Srinivasa, Ashish Kundu, Mingyi Hong, Jie Ding · 25 décembre 2025

  Data science plays a critical role in transforming complex data into actionable insights across numerous domains. Recent developments in large language models (LLMs) have significantly automated data science workflows, but a fundamental question persists: Can these agentic AI systems truly match the…

• Improving Coverage in Combined Prediction Sets with Weighted p-values

  Gina Wong, Drew Prinster, Suchi Saria, Rama Chellappa, Anqi Liu · 25 décembre 2025

  Conformal prediction quantifies the uncertainty of machine learning models by augmenting point predictions with valid prediction sets. For complex scenarios involving multiple trials, models, or data sources, conformal prediction sets can be aggregated to create a prediction set that captures the ov…

• Reward Is Enough: LLMs Are In-Context Reinforcement Learners

  Kefan Song, Amir Moeini, Peng Wang, Lei Gong, Rohan Chandra, Yanjun Qi, Shangtong Zhang · 25 décembre 2025

  Reinforcement learning (RL) is a framework for solving sequential decision-making problems. In this work, we demonstrate that, surprisingly, RL emerges during the inference time of large language models (LLMs), a phenomenon we term in-context RL (ICRL). To reveal this capability, we introduce a simp…

• FaithLens: Detecting and Explaining Faithfulness Hallucination

  Shuzheng Si, Qingyi Wang, Haozhe Zhao, Yuzhuo Bai, Guanqiao Chen, Kangyang Luo, Gang Chen, Fanchao Qi, Minjia Zhang, Baobao Chang, Maosong Sun · 24 décembre 2025

  Recognizing whether outputs from large language models (LLMs) contain faithfulness hallucination is crucial for real-world applications, e.g., retrieval-augmented generation and summarization. In this paper, we introduce FaithLens, a cost-efficient and effective faithfulness hallucination detection …

• UbiQVision: Quantifying Uncertainty in XAI for Image Recognition

  Akshat Dubey, Aleksandar An\v{z}el, Bahar \.Ilgen, Georges Hattab · 24 décembre 2025

  Recent advances in deep learning have led to its widespread adoption across diverse domains, including medical imaging. This progress is driven by increasingly sophisticated model architectures, such as ResNets, Vision Transformers, and Hybrid Convolutional Neural Networks, that offer enhanced perfo…

• Explainable time-series forecasting with sampling-free SHAP for Transformers

  Matthias Hertel, Sebastian P\"utz, Ralf Mikut, Veit Hagenmeyer, Benjamin Sch\"afer · 24 décembre 2025

  Time-series forecasts are essential for planning and decision-making in many domains. Explainability is key to building user trust and meeting transparency requirements. Shapley Additive Explanations (SHAP) is a popular explainable AI framework, but it lacks efficient implementations for time series…

• The Deleuzian Representation Hypothesis

  Cl\'ement Cornet, Romaric Besan\c{c}on, Herv\'e Le Borgne · 24 décembre 2025

  We propose an alternative to sparse autoencoders (SAEs) as a simple and effective unsupervised method for extracting interpretable concepts from neural networks. The core idea is to cluster differences in activations, which we formally justify within a discriminant analysis framework. To enhance the…

• Explainable deep learning improves human mental models of self-driving cars

  Eoin M. Kenny, Akshay Dharmavaram, Sang Uk Lee, Tung Phan-Minh, Shreyas Rajesh, Yunqing Hu, Laura Major, Momchil S. Tomov, Julie A. Shah · 24 décembre 2025

  Self-driving cars increasingly rely on deep neural networks to achieve human-like driving. The opacity of such black-box planners makes it challenging for the human behind the wheel to accurately anticipate when they will fail, with potentially catastrophic consequences. While research into interpre…

• Toward Explaining Large Language Models in Software Engineering Tasks

  Antonio Vitale, Khai-Nguyen Nguyen, Denys Poshyvanyk, Rocco Oliveto, Simone Scalabrino, Antonio Mastropaolo · 24 décembre 2025

  Recent progress in Large Language Models (LLMs) has substantially advanced the automation of software engineering (SE) tasks, enabling complex activities such as code generation and code summarization. However, the black-box nature of LLMs remains a major barrier to their adoption in high-stakes and…

• DeepBridge: A Unified and Production-Ready Framework for Multi-Dimensional Machine Learning Validation

  Gustavo Coelho Haase, Paulo Henrique Dourado da Silva · 24 décembre 2025

  We present DeepBridge, an 80K-line Python library that unifies multi-dimensional validation, automatic compliance verification, knowledge distillation, and synthetic data generation. DeepBridge offers: (i) 5 validation suites (fairness with 15 metrics, robustness with weakness detection, uncertainty…

• BRIDGE: Budget-aware Reasoning via Intermediate Distillation with Guided Examples

  Xuan-An Le, Minh-Nam Tran, Son Nguyen · 24 décembre 2025

  Distilling knowledge from large proprietary models (e.g., GPT-4) to tiny deployable models (less than 1B parameters) faces a critical capacity-budget trap: the 1000x capacity gap between teachers and students prevents effective direct transfer, while API costs prohibit extensive data collection. We …

• ABBEL: LLM Agents Acting through Belief Bottlenecks Expressed in Language

  Aly Lidayan, Jakob Bjorner, Satvik Golechha, Kartik Goyal, Alane Suhr · 24 décembre 2025

  As the length of sequential decision-making tasks increases, it becomes computationally impractical to keep full interaction histories in context. We introduce a general framework for LLM agents to maintain concise contexts through multi-step interaction: Acting through Belief Bottlenecks Expressed …

• KAN-AFT: An Interpretable Nonlinear Survival Model Integrating Kolmogorov-Arnold Networks with Accelerated Failure Time Analysis

  Mebin Jose, Jisha Francis, Sudheesh Kumar Kattumannil · 24 décembre 2025

  Survival analysis relies fundamentally on the semi-parametric Cox Proportional Hazards (CoxPH) model and the parametric Accelerated Failure Time (AFT) model. CoxPH assumes constant hazard ratios, often failing to capture real-world dynamics, while traditional AFT models are limited by rigid distribu…

• The Procrustean Bed of Time Series: The Optimization Bias of Point-wise Loss

  Rongyao Cai, Yuxi Wan, Kexin Zhang, Ming Jin, Hao Wang, Zhiqiang Ge, Daoyi Dong, Yong Liu, Qingsong Wen · 23 décembre 2025

  Optimizing time series models via point-wise loss functions (e.g., MSE) relying on a flawed point-wise independent and identically distributed (i.i.d.) assumption that disregards the causal temporal structure, an issue with growing awareness yet lacking formal theoretical grounding. Focusing on the …

• Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environments

  Geraud Nangue Tasse, Matthew Riemer, Benjamin Rosman, Tim Klinger · 23 décembre 2025

  Recent success in developing increasingly general purpose agents based on sequence models has led to increased focus on the problem of deploying computationally limited agents within the vastly more complex real-world. A key challenge experienced in these more realistic domains is highly non-Markovi…

• Faithful and Stable Neuron Explanations for Trustworthy Mechanistic Interpretability

  Ge Yan (Lily), Tuomas Oikarinen (Lily), Tsui-Wei (Lily), Weng · 23 décembre 2025

  Neuron identification is a popular tool in mechanistic interpretability, aiming to uncover the human-interpretable concepts represented by individual neurons in deep networks. While algorithms such as Network Dissection and CLIP-Dissect achieve great empirical success, a rigorous theoretical foundat…

• CORE: Concept-Oriented Reinforcement for Bridging the Definition-Application Gap in Mathematical Reasoning

  Zijun Gao, Zhikun Xu, Xiao Ye, Ben Zhou · 23 décembre 2025

  Large language models (LLMs) often solve challenging math exercises yet fail to apply the concept right when the problem requires genuine understanding. Popular Reinforcement Learning with Verifiable Rewards (RLVR) pipelines reinforce final answers but provide little fine-grained conceptual signal, …

• The Erasure Illusion: Stress-Testing the Generalization of LLM Forgetting Evaluation

  Hengrui Jia, Taoran Li, Jonas Guan, Varun Chandrasekaran · 23 décembre 2025

  Machine unlearning aims to remove specific data influences from trained models, a capability essential for adhering to copyright laws and ensuring AI safety. Current unlearning metrics typically measure success by monitoring the model's performance degradation on the specific unlearning dataset ($D_…

• VIGOR+: Iterative Confounder Generation and Validation via LLM-CEVAE Feedback Loop

  JiaWei Zhu, ZiHeng Liu · 23 décembre 2025

  Hidden confounding remains a fundamental challenge in causal inference from observational data. Recent advances leverage Large Language Models (LLMs) to generate plausible hidden confounders based on domain knowledge, yet a critical gap exists: LLM-generated confounders often exhibit semantic plausi…

• From Points to Coalitions: Hierarchical Contrastive Shapley Values for Prioritizing Data Samples

  Canran Xiao, Jiabao Dou, Zhiming Lin, Zong Ke, Liwei Hou · 23 décembre 2025

  How should we quantify the value of each training example when datasets are large, heterogeneous, and geometrically structured? Classical Data-Shapley answers in principle, but its O(n!) complexity and point-wise perspective are ill-suited to modern scales. We propose Hierarchical Contrastive Data V…

• Cluster-Based Generalized Additive Models Informed by Random Fourier Features

  Xin Huang, Jia Li, Jun Yu · 23 décembre 2025

  Explainable machine learning aims to strike a balance between prediction accuracy and model transparency, particularly in settings where black-box predictive models, such as deep neural networks or kernel-based methods, achieve strong empirical performance but remain difficult to interpret. This wor…

• Zero-Overhead Introspection for Adaptive Test-Time Compute

  Rohin Manvi, Joey Hong, Tim Seyde, Maxime Labonne, Mathias Lechner, Sergey Levine · 23 décembre 2025

  Large language models excel at reasoning but lack key aspects of introspection, including anticipating their own success and the computation required to achieve it. Humans use real-time introspection to decide how much effort to invest, when to make multiple attempts, when to stop, and when to signa…

• Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward

  Peter Chen, Xiaopeng Li, Ziniu Li, Wotao Yin, Xi Chen, Tianyi Lin · 23 décembre 2025

  This paper examines the exploration-exploitation trade-off in reinforcement learning with verifiable rewards (RLVR), a framework for improving the reasoning of Large Language Models (LLMs). Recent studies suggest that RLVR can elicit strong mathematical reasoning in LLMs through two seemingly parado…