Explainable Artificial Intelligence (XAI)

Derniers papiers

• JADE: Expert-Grounded Dynamic Evaluation for Open-Ended Professional Tasks

  Lanbo Lin, Jiayao Liu, Tianyuan Yang, Li Cai, Yuanwu Xu, Lei Wei, Sicong Xie, Guannan Zhang · 9 février 2026

  Evaluating agentic AI on open-ended professional tasks faces a fundamental dilemma between rigor and flexibility. Static rubrics provide rigorous, reproducible assessment but fail to accommodate diverse valid response strategies, while LLM-as-a-judge approaches adapt to individual responses yet suff…

• From Features to Actions: Explainability in Traditional and Agentic AI Systems

  Sindhuja Chaduvula, Jessee Ho, Kina Kim, Aravind Narayanan, Mahshid Alinoori, Muskan Garg, Dhanesh Ramachandram, Shaina Raza · 9 février 2026

  Over the last decade, explainable AI has primarily focused on interpreting individual model predictions, producing post-hoc explanations that relate inputs to outputs under a fixed decision structure. Recent advances in large language models (LLMs) have enabled agentic AI systems whose behaviour unf…

• The Quantum Sieve Tracer: A Hybrid Framework for Layer-Wise Activation Tracing in Large Language Models

  Jonathan Pan · 9 février 2026

  Mechanistic interpretability aims to reverse-engineer the internal computations of Large Language Models (LLMs), yet separating sparse semantic signals from high-dimensional polysemantic noise remains a significant challenge. This paper introduces the Quantum Sieve Tracer, a hybrid quantum-classical…

• SR4-Fit: An Interpretable and Informative Classification Algorithm Applied to Prediction of U.S. House of Representatives Elections

  Shyam Sundar Murali Krishnan, Dean Frederick Hougen · 9 février 2026

  The growth of machine learning demands interpretable models for critical applications, yet most high-performing models are ``black-box'' systems that obscure input-output relationships, while traditional rule-based algorithms like RuleFit suffer from a lack of predictive power and instability despit…

• Always Keep Your Promises: A Model-Agnostic Attribution Algorithm for Neural Networks

  Kevin Lee, Duncan Smith-Halverson, Pablo Millan Arias · 9 février 2026

  Layer-wise Relevance Propagation (LRP) provides principled attribution for neural networks through conservation properties and foundations in Deep Taylor Decomposition. However, existing implementations operate at the module level, requiring architecture-specific propagation rules and model modifica…

• Generating Data-Driven Reasoning Rubrics for Domain-Adaptive Reward Modeling

  Kate Sanders, Nathaniel Weir, Sapana Chaudhary, Kaj Bostrom, Huzefa Rangwala · 9 février 2026

  An impediment to using Large Language Models (LLMs) for reasoning output verification is that LLMs struggle to reliably identify errors in thinking traces, particularly in long outputs, domains requiring expert knowledge, and problems without verifiable rewards. We propose a data-driven approach to …

• Adaptive Uncertainty-Aware Tree Search for Robust Reasoning

  Zeen Song, Zihao Ma, Wenwen Qiang, Changwen Zheng, Gang Hua · 9 février 2026

  Inference-time reasoning scaling has significantly advanced the capabilities of Large Language Models (LLMs) in complex problem-solving. A prevalent approach involves external search guided by Process Reward Models (PRMs). However, a fundamental limitation of this framework is the epistemic uncertai…

• ProtoQuant: Quantization of Prototypical Parts For General and Fine-Grained Image Classification

  Miko{\l}aj Janusz, Adam Wr\'obel, Bartosz Zieli\'nski, Dawid Rymarczyk · 9 février 2026

  Prototypical parts-based models offer a "this looks like that" paradigm for intrinsic interpretability, yet they typically struggle with ImageNet-scale generalization and often require computationally expensive backbone finetuning. Furthermore, existing methods frequently suffer from "prototype drif…

• Reasoning-guided Collaborative Filtering with Language Models for Explainable Recommendation

  Fahad Anwaar, Adil Mehmood Khan, Muhammad Khalid, Usman Zia, Kezhi Wang · 6 février 2026

  Large Language Models (LLMs) exhibit potential for explainable recommendation systems but overlook collaborative signals, while prevailing methods treat recommendation and explanation as separate tasks, resulting in a memory footprint. We present RGCF-XRec, a hybrid framework that introduces reasoni…

• Understanding LLM Evaluator Behavior: A Structured Multi-Evaluator Framework for Merchant Risk Assessment

  Liang Wang, Junpeng Wang, Chin-chia Michael Yeh, Yan Zheng, Jiarui Sun, Xiran Fan, Xin Dai, Yujie Fan, Yiwei Cai · 6 février 2026

  Large Language Models (LLMs) are increasingly used as evaluators of reasoning quality, yet their reliability and bias in payments-risk settings remain poorly understood. We introduce a structured multi-evaluator framework for assessing LLM reasoning in Merchant Category Code (MCC)-based merchant ris…

• DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders

  Xu Wang, Bingqing Jiang, Yu Wan, Baosong Yang, Lingpeng Kong, Difan Zou · 6 février 2026

  Sparse autoencoders (SAEs) have become a standard tool for mechanistic interpretability in autoregressive large language models (LLMs), enabling researchers to extract sparse, human-interpretable features and intervene on model behavior. Recently, as diffusion language models (DLMs) have become an i…

• Reliable Explanations or Random Noise? A Reliability Metric for XAI

  Poushali Sengupta, Sabita Maharjan, Frank Eliassen, Shashi Raj Pandey, Yan Zhang · 6 février 2026

  In recent years, explaining decisions made by complex machine learning models has become essential in high-stakes domains such as energy systems, healthcare, finance, and autonomous systems. However, the reliability of these explanations, namely, whether they remain stable and consistent under reali…

• Auto-Rubric: Learning From Implicit Weights to Explicit Rubrics for Reward Modeling

  Lipeng Xie, Sen Huang, Zhuo Zhang, Anni Zou, Yunpeng Zhai, Dingchao Ren, Kezun Zhang, Haoyuan Hu, Boyin Liu, Haoran Chen, Zhaoyang Liu, Bolin Ding · 6 février 2026

  Conventional reward modeling relies on gradient descent over neural weights, creating opaque, data-hungry "black boxes." We propose a paradigm shift from implicit to explicit reward parameterization, recasting optimization from continuous weight spaces to the discrete space of natural language rubri…

• PATHWAYS: Evaluating Investigation and Context Discovery in AI Web Agents

  Shifat E. Arman, Syed Nazmus Sakib, Tapodhir Karmakar Taton, Nafiul Haque, Shahrear Bin Amin · 6 février 2026

  We introduce PATHWAYS, a benchmark of 250 multi-step decision tasks that test whether web-based agents can discover and correctly use hidden contextual information. Across both closed and open models, agents typically navigate to relevant pages but retrieve decisive hidden evidence in only a small f…

• Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks

  William F. Shen, Xinchi Qiu, Chenxi Whitehouse, Lisa Alazraki, Shashwat Goel, Francesco Barbieri, Timon Willi, Akhil Mathur, Ilias Leontiadis · 6 février 2026

  Recently, rubrics have been used to guide LLM judges in capturing subjective, nuanced, multi-dimensional human preferences, and have been extended from evaluation to reward signals for reinforcement fine-tuning (RFT). However, rubric generation remains hard to control: rubrics often lack coverage, c…

• Towards Worst-Case Guarantees with Scale-Aware Interpretability

  Lauren Greenspan, David Berman, Aryeh Brill, Ro Jefferson, Artemy Kolchinsky, Jennifer Lin, Andrew Mack, Anindita Maiti, Fernando E. Rosas, Alexander Stapleton, Lucas Teixeira, Dmitry Vaintrob · 6 février 2026

  Neural networks organize information according to the hierarchical, multi-scale structure of natural data. Methods to interpret model internals should be similarly scale-aware, explicitly tracking how features compose across resolutions and guaranteeing bounds on the influence of fine-grained struct…

• Hidden in Plain Sight -- Class Competition Focuses Attribution Maps

  Nils Philipp Walter, Jilles Vreeken, Jonas Fischer · 6 février 2026

  Attribution methods reveal which input features a neural network uses for a prediction, adding transparency to their decisions. A common problem is that these attributions seem unspecific, highlighting both important and irrelevant features. We revisit the common attribution pipeline and observe tha…

• Explanations are a Means to an End: Decision Theoretic Explanation Evaluation

  Ziyang Guo, Berk Ustun, Jessica Hullman · 6 février 2026

  Explanations of model behavior are commonly evaluated via proxy properties weakly tied to the purposes explanations serve in practice. We contribute a decision theoretic framework that treats explanations as information signals valued by the expected improvement they enable on a specified decision t…

• NEX: Neuron Explore-Exploit Scoring for Label-Free Chain-of-Thought Selection and Model Ranking

  Kang Chen, Zhuoka Feng, Sihan Zhao, Kai Xiong, Junjie Nian, Yaoning Wang, Changyi Xiao, Yixin Cao · 6 février 2026

  Large language models increasingly spend inference compute sampling multiple chain-of-thought traces or searching over merged checkpoints. This shifts the bottleneck from generation to selection, often without supervision on the target distribution. We show entropy-based exploration proxies follow a…

• Momentum Attention: The Physics of In-Context Learning and Spectral Forensics for Mechanistic Interpretability

  Kingsuk Maitra · 6 février 2026

  The Mechanistic Interpretability (MI) program has mapped the Transformer as a precise computational graph. We extend this graph with a conservation law and time-varying AC dynamics, viewing it as a physical circuit. We introduce Momentum Attention, a symplectic augmentation embedding physical priors…

• Hinge Regression Tree: A Newton Method for Oblique Regression Tree Splitting

  Hongyi Li, Han Lin, Jun Xu · 6 février 2026

  Oblique decision trees combine the transparency of trees with the power of multivariate decision boundaries, but learning high-quality oblique splits is NP-hard, and practical methods still rely on slow search or theory-free heuristics. We present the Hinge Regression Tree (HRT), which reframes each…

• Data-Centric Interpretability for LLM-based Multi-Agent Reinforcement Learning

  John Yan, Michael Yu, Yuqi Sun, Alexander Duffy, Tyler Marques, Matthew Lyle Olson · 6 février 2026

  Large language models (LLMs) are increasingly trained in complex Reinforcement Learning, multi-agent environments, making it difficult to understand how behavior changes over training. Sparse Autoencoders (SAEs) have recently shown to be useful for data-centric interpretability. In this work, we ana…

• Explainable AI: A Combined XAI Framework for Explaining Brain Tumour Detection Models

  Patrick McGonagle, William Farrelly, Kevin Curran · 6 février 2026

  This study explores the integration of multiple Explainable AI (XAI) techniques to enhance the interpretability of deep learning models for brain tumour detection. A custom Convolutional Neural Network (CNN) was developed and trained on the BraTS 2021 dataset, achieving 91.24% accuracy in distinguis…

• CFRecs: Counterfactual Recommendations on Real Estate User Listing Interaction Graphs

  Seyedmasoud Mousavi, Ruomeng Xu, Xiaojing Zhu · 6 février 2026

  Graph-structured data is ubiquitous and powerful in representing complex relationships in many online platforms. While graph neural networks (GNNs) are widely used to learn from such data, counterfactual graph learning has emerged as a promising approach to improve model interpretability. Counterfac…

• Scalable Explainability-as-a-Service (XaaS) for Edge AI Systems

  Samaresh Kumar Singh, Joyjit Roy · 5 février 2026

  Though Explainable AI (XAI) has made significant advancements, its inclusion in edge and IoT systems is typically ad-hoc and inefficient. Most current methods are "coupled" in such a way that they generate explanations simultaneously with model inferences. As a result, these approaches incur redunda…