Explainable Artificial Intelligence (XAI)

Derniers papiers

• Neural Scaling Laws for Boosted Jet Tagging

  Matthias Vigl, Nicole Hartman, Michael Kagan, Lukas Heinrich · 18 février 2026

  The success of Large Language Models (LLMs) has established that scaling compute, through joint increases in model capacity and dataset size, is the primary driver of performance in modern machine learning. While machine learning has long been an integral component of High Energy Physics (HEP) data …

• CEPAE: Conditional Entropy-Penalized Autoencoders for Time Series Counterfactuals

  Tom\`as Garriga, Gerard Sanz, Eduard Serrahima de Cambra, Axel Brando · 18 février 2026

  The ability to accurately perform counterfactual inference on time series is crucial for decision-making in fields like finance, healthcare, and marketing, as it allows us to understand the impact of events or treatments on outcomes over time. In this paper, we introduce a new counterfactual inferen…

• Recursive Concept Evolution for Compositional Reasoning in Large Language Models

  Sarim Chaudhry · 18 février 2026

  Large language models achieve strong performance on many complex reasoning tasks, yet their accuracy degrades sharply on benchmarks that require compositional reasoning, including ARC-AGI-2, GPQA, MATH, BBH, and HLE. Existing methods improve reasoning by expanding token-level search through chain-of…

• Logit Distance Bounds Representational Similarity

  Beatrix M. B. Nielsen, Emanuele Marconato, Luigi Gresele, Andrea Dittadi, Simon Buchholz · 18 février 2026

  For a broad family of discriminative models that includes autoregressive language models, identifiability results imply that if two models induce the same conditional distributions, then their internal representations agree up to an invertible linear transformation. We ask whether an analogous concl…

• Indic-TunedLens: Interpreting Multilingual Models in Indian Languages

  Mihir Panchal, Deeksha Varshney, Mamta, Asif Ekbal · 18 février 2026

  Multilingual large language models (LLMs) are increasingly deployed in linguistically diverse regions like India, yet most interpretability tools remain tailored to English. Prior work reveals that LLMs often operate in English centric representation spaces, making cross lingual interpretability a p…

• GenAI-LA: Generative AI and Learning Analytics Workshop (LAK 2026), April 27--May 1, 2026, Bergen, Norway

  Javier Irigoyen, Roberto Daza, Aythami Morales, Julian Fierrez, Francisco Jurado, Alvaro Ortigosa, Ruben Tolosana · 18 février 2026

  This work introduces EduEVAL-DB, a dataset based on teacher roles designed to support the evaluation and training of automatic pedagogical evaluators and AI tutors for instructional explanations. The dataset comprises 854 explanations corresponding to 139 questions from a curated subset of the Scien…

• Discovering Implicit Large Language Model Alignment Objectives

  Edward Chen, Sanmi Koyejo, Carlos Guestrin · 18 février 2026

  Large language model (LLM) alignment relies on complex reward signals that often obscure the specific behaviors being incentivized, creating critical risks of misalignment and reward hacking. Existing interpretation methods typically rely on pre-defined rubrics, risking the omission of "unknown unkn…

• Mind the (DH) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLMs

  Luise Ge, Yongyan Zhang, Yevgeniy Vorobeychik · 18 février 2026

  The use of large language models either as decision support systems, or in agentic workflows, is rapidly transforming the digital ecosystem. However, the understanding of LLM decision-making under uncertainty remains limited. We initiate a comparative study of LLM risky choices along two dimensions:…

• Automatically Finding Reward Model Biases

  Atticus Wang, Iv\'an Arcuschin, Arthur Conmy · 18 février 2026

  Reward models are central to large language model (LLM) post-training. However, past work has shown that they can reward spurious or undesirable attributes such as length, format, hallucinations, and sycophancy. In this work, we introduce and study the research problem of automatically finding rewar…

• Sparse Autoencoders for Sequential Recommendation Models: Interpretation and Flexible Control

  Anton Klenitskiy, Konstantin Polev, Daria Denisova, Alexey Vasilev, Dmitry Simakov, Gleb Gusev · 18 février 2026

  Many current state-of-the-art models for sequential recommendations are based on transformer architectures. Interpretation and explanation of such black box models is an important research question, as a better understanding of their internals can help understand, influence, and control their behavi…

• Directional Reasoning Trajectory Change (DRTC): Identifying Critical Trace Segments in Reasoning Models

  Waldemar Chang · 18 février 2026

  Understanding how language models carry out long-horizon reasoning remains an open challenge. Existing interpretability methods often highlight tokens or spans correlated with an answer, but they rarely reveal where the model makes consequential reasoning turns, which earlier context causally trigge…

• Comparables XAI: Faithful Example-based AI Explanations with Counterfactual Trace Adjustments

  Yifan Zhang, Tianle Ren, Fei Wang, Brian Y Lim · 17 février 2026

  Explaining with examples is an intuitive way to justify AI decisions. However, it is challenging to understand how a decision value should change relative to the examples with many features differing by large amounts. We draw from real estate valuation that uses Comparables-examples with known value…

• The Well-Tempered Classifier: Some Elementary Properties of Temperature Scaling

  Pierre-Alexandre Mattei, Bruno Loureiro · 17 février 2026

  Temperature scaling is a simple method that allows to control the uncertainty of probabilistic models. It is mostly used in two contexts: improving the calibration of classifiers and tuning the stochasticity of large language models (LLMs). In both cases, temperature scaling is the most popular meth…

• Bridging AI and Clinical Reasoning: Abductive Explanations for Alignment on Critical Symptoms

  Belona Sonna, Alban Grastien · 17 février 2026

  Artificial intelligence (AI) has demonstrated strong potential in clinical diagnostics, often achieving accuracy comparable to or exceeding that of human experts. A key challenge, however, is that AI reasoning frequently diverges from structured clinical frameworks, limiting trust, interpretability,…

• The Sufficiency-Conciseness Trade-off in LLM Self-Explanation from an Information Bottleneck Perspective

  Ali Zahedzadeh, Behnam Bahrak · 17 février 2026

  Large Language Models increasingly rely on self-explanations, such as chain of thought reasoning, to improve performance on multi step question answering. While these explanations enhance accuracy, they are often verbose and costly to generate, raising the question of how much explanation is truly n…

• Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets

  Yuchen Yang, Wenze Lin, Enhao Huang, Zhixuan Chu, Hongbin Zhou, Lan Tao, Yiming Li, Zhan Qin, Kui Ren · 17 février 2026

  Large Language Models (LLMs) have seen remarkable advancements, achieving state-of-the-art results in diverse applications. Fine-tuning, an important step for adapting LLMs to specific downstream tasks, typically involves further training on corresponding datasets. However, a fundamental discrepancy…

• Interpretable clustering via optimal multiway-split decision trees

  Hayato Suzuki, Shunnosuke Ikeda, Yuichi Takano · 17 février 2026

  Clustering serves as a vital tool for uncovering latent data structures, and achieving both high accuracy and interpretability is essential. To this end, existing methods typically construct binary decision trees by solving mixed-integer nonlinear optimization problems, often leading to significant …

• Explanatory Interactive Machine Learning for Bias Mitigation in Visual Gender Classification

  Nathanya Satriani, Djordje Slijep\v{c}evi\'c, Markus Schedl, Matthias Zeppelzauer · 17 février 2026

  Explanatory interactive learning (XIL) enables users to guide model training in machine learning (ML) by providing feedback on the model's explanations, thereby helping it to focus on features that are relevant to the prediction from the user's perspective. In this study, we explore the capability o…

• Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5

  Dongrui Liu, Yi Yu, Jie Zhang, Guanxu Chen, Qihao Lin, Hanxi Zhu, Lige Huang, Yijin Zhou, Peng Wang, Shuai Shao, Boxuan Zhang, Zicheng Liu, Jingwei Sun, Yu Li, Yuejin Xie, Jiaxuan Guo, Jia Xu, Chaochao Lu, Bowen Zhou, Xia Hu, Jing Shao · 17 février 2026

  To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework in Practice presents a comprehensive assessment of their frontier risks. As Large Language Models (LLMs) general capabilities rapidly evolve and th…

• Contrastive explanations of BDI agents

  Michael Winikoff · 17 février 2026

  The ability of autonomous systems to provide explanations is important for supporting transparency and aiding the development of (appropriate) trust. Prior work has defined a mechanism for Belief-Desire-Intention (BDI) agents to be able to answer questions of the form ``why did you do action $X$?''.…

• Benchmarking at the Edge of Comprehension

  Samuele Marro, Jialin Yu, Emanuele La Malfa, Oishi Deb, Jiawei Li, Yibo Yang, Ebey Abraham, Sunando Sengupta, Eric Sommerlade, Michael Wooldridge, Philip Torr · 17 février 2026

  As frontier Large Language Models (LLMs) increasingly saturate new benchmarks shortly after they are published, benchmarking itself is at a juncture: if frontier models keep improving, it will become increasingly hard for humans to generate discriminative tasks, provide accurate ground-truth answers…

• Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution

  Matthew Kowal, Goncalo Paulo, Louis Jaburi, Tom Tseng, Lev E McKinney, Stefan Heimersheim, Aaron David Tucker, Adam Gleave, Kellin Pelrine · 17 février 2026

  As large language models are increasingly trained and fine-tuned, practitioners need methods to identify which training data drive specific behaviors, particularly unintended ones. Training Data Attribution (TDA) methods address this by estimating datapoint influence. Existing approaches like influe…

• Transferable XAI: Relating Understanding Across Domains with Explanation Transfer

  Fei Wang, Yifan Zhang, Brian Y. Lim · 17 février 2026

  Current Explainable AI (XAI) focuses on explaining a single application, but when encountering related applications, users may rely on their prior understanding from previous explanations. This leads to either overgeneralization and AI overreliance, or burdensome independent memorization. Indeed, re…

• Singular Vectors of Attention Heads Align with Features

  Gabriel Franco, Carson Loughridge, Mark Crovella · 17 février 2026

  Identifying feature representations in language models is a central task in mechanistic interpretability. Several recent studies have made an implicit assumption that feature representations can be inferred in some cases from singular vectors of attention matrices. However, sound justification for t…

• Learning to Select Like Humans: Explainable Active Learning for Medical Imaging

  Ifrat Ikhtear Uddin, Longwei Wang, Xiao Qin, Yang Zhou, KC Santosh · 17 février 2026

  Medical image analysis requires substantial labeled data for model training, yet expert annotation is expensive and time-consuming. Active learning (AL) addresses this challenge by strategically selecting the most informative samples for the annotation purpose, but traditional methods solely rely on…