Explainable Artificial Intelligence (XAI)

Derniers papiers

• Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery

  Xuemin Yu, Ankur Garg, Samira Ebrahimi Kahou, Hassan Sajjad · 4 février 2026

  Deep Learning models encode rich semantic information in their hidden representations. However, it remains challenging to understand which parts of this information models actually rely on when making predictions. A promising line of post-hoc concept-based explanation methods relies on clustering to…

• Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks

  Bohan Wang, Zewen Liu, Lu Lin, Hui Liu, Li Xiong, Ming Jin, Wei Jin · 4 février 2026

  Interpretable time series deep learning systems are often assessed by checking temporal consistency on explanations, implicitly treating this as evidence of robustness. We show that this assumption can fail: Predictions and explanations can be adversarially decoupled, enabling targeted misclassifica…

• A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior

  Harry Mayne, Justin Singh Kang, Dewi Gould, Kannan Ramchandran, Adam Mahdi, Noah Y. Siegel · 4 février 2026

  LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning process is poorly understood. Existing faithfulness metrics have critical limitations, typically relying on identifying unfaithfulness via adversarial prompting or det…

• Conformal Thinking: Risk Control for Reasoning on a Compute Budget

  Xi Wang, Anushri Suresh, Alvin Zhang, Rishi More, William Jurayj, Benjamin Van Durme, Mehrdad Farajtabar, Daniel Khashabi, Eric Nalisnick · 4 février 2026

  Reasoning Large Language Models (LLMs) enable test-time scaling, with dataset-level accuracy improving as the token budget increases, motivating adaptive reasoning -- spending tokens when they improve reliability and stopping early when additional computation is unlikely to help. However, setting th…

• Mixture of Concept Bottleneck Experts

  Francesco De Santis, Gabriele Ciravegna, Giovanni De Felice, Arianna Casanova, Francesco Giannini, Michelangelo Diligenti, Mateo Espinosa Zarlenga, Pietro Barbiero, Johannes Schneider, Danilo Giordano · 4 février 2026

  Concept Bottleneck Models (CBMs) promote interpretability by grounding predictions in human-understandable concepts. However, existing CBMs typically fix their task predictor to a single linear or Boolean expression, limiting both predictive accuracy and adaptability to diverse user needs. We propos…

• QuantLRM: Quantization of Large Reasoning Models via Fine-Tuning Signals

  Nan Zhang, Eugene Kwek, Yusen Zhang, Muyu Pan, Suhang Wang, Prasenjit Mitra, Rui Zhang · 4 février 2026

  Weight-only quantization is important for compressing Large Language Models (LLMs). Inspired by the spirit of classical magnitude pruning, we study whether the magnitude of weight updates during reasoning-incentivized fine-tuning can provide valuable signals for quantizing Large Reasoning Models (LR…

• LEMON: Local Explanations via Modality-aware OptimizatioN

  Yu Qin, Phillip Sloan, Raul Santos-Rodriguez, Majid Mirmehdi, Telmo de Menezes e Silva Filho · 4 février 2026

  Multimodal models are ubiquitous, yet existing explainability methods are often single-modal, architecture-dependent, or too computationally expensive to run at scale. We introduce LEMON (Local Explanations via Modality-aware OptimizatioN), a model-agnostic framework for local explanations of multim…

• Explanations Leak: Membership Inference with Differential Privacy and Active Learning Defense

  Fatima Ezzeddine, Osama Zammar, Silvia Giordano, Omran Ayoub · 4 février 2026

  Counterfactual explanations (CFs) are increasingly integrated into Machine Learning as a Service (MLaaS) systems to improve transparency; however, ML models deployed via APIs are already vulnerable to privacy attacks such as membership inference and model extraction, and the impact of explanations o…

• Self-Verification Dilemma: Experience-Driven Suppression of Overused Checking in LLM Reasoning

  Quanyu Long, Kai Jie Jiang, Jianda Chen, Xu Guo, Leilei Gan, Wenya Wang · 4 février 2026

  Large Reasoning Models (LRMs) achieve strong performance by generating long reasoning traces with reflection. Through a large-scale empirical analysis, we find that a substantial fraction of reflective steps consist of self-verification (recheck) that repeatedly confirm intermediate results. These r…

• Evaluating LLMs When They Do Not Know the Answer: Statistical Evaluation of Mathematical Reasoning via Comparative Signals

  Zihan Dong, Zhixian Zhang, Yang Zhou, Can Jin, Ruijia Wu, Linjun Zhang · 4 février 2026

  Evaluating mathematical reasoning in LLMs is constrained by limited benchmark sizes and inherent model stochasticity, yielding high-variance accuracy estimates and unstable rankings across platforms. On difficult problems, an LLM may fail to produce a correct final answer, yet still provide reliable…

• From Task Solving to Robust Real-World Adaptation in LLM Agents

  Pouya Pezeshkpour, Estevam Hruschka · 4 février 2026

  Large language models are increasingly deployed as specialized agents that plan, call tools, and take actions over extended horizons. Yet many existing evaluations assume a "clean interface" where dynamics are specified and stable, tools and sensors are reliable, and success is captured by a single …

• LLM-Inspired Pretrain-Then-Finetune for Small-Data, Large-Scale Optimization

  Zishi Zhang, Jinhui Han, Ming Hu, Yijie Peng · 4 février 2026

  We consider small-data, large-scale decision problems in which a firm must make many operational decisions simultaneously (e.g., across a large product portfolio) while observing only a few, potentially noisy, data points per instance. Inspired by the success of large language models (LLMs), we prop…

• Stream: Scaling up Mechanistic Interpretability to Long Context in LLMs via Sparse Attention

  J Rosser, Jos\'e Luis Redondo Garc\'ia, Gustavo Penha, Konstantina Palla, Hugues Bouchard · 3 février 2026

  As Large Language Models (LLMs) scale to million-token contexts, traditional Mechanistic Interpretability techniques for analyzing attention scale quadratically with context length, demanding terabytes of memory beyond 100,000 tokens. We introduce Sparse Tracing, a novel technique that leverages dyn…

• Transferring Visual Explainability of Self-Explaining Models to Prediction-Only Models without Additional Training

  Yuya Yoshikawa, Ryotaro Shimizu, Takahiro Kawashima, Yuki Saito · 3 février 2026

  In image classification scenarios where both prediction and explanation efficiency are required, self-explaining models that perform both tasks in a single inference are effective. However, for users who already have prediction-only models, training a new self-explaining model from scratch imposes s…

• Your Latent Reasoning is Secretly Policy Improvement Operator

  Arip Asadulaev, Rayan Banerjee, Fakhri Karray, Martin Takac · 3 février 2026

  Recently, small models with latent recursion have obtained promising results on complex reasoning tasks. These results are typically explained by the theory that such recursion increases a networks depth, allowing it to compactly emulate the capacity of larger models. However, the performance of rec…

• Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet

  James Xu Zhao, Bryan Hooi, See-Kiong Ng · 3 février 2026

  Test-time scaling increases inference-time computation by allowing models to generate long reasoning chains, and has improved performance across many domains. However, in this work, we show that this approach is not yet effective for knowledge-intensive tasks. We evaluate 14 reasoning models on two …

• ReasonCACHE: Teaching LLMs To Reason Without Weight Updates

  Sharut Gupta, Phillip Isola, Stefanie Jegelka, David Lopez-Paz, Kartik Ahuja, Mark Ibrahim, Mohammad Pezeshki · 3 février 2026

  Can Large language models (LLMs) learn to reason without any weight update and only through in-context learning (ICL)? ICL is strikingly sample-efficient, often learning from only a handful of demonstrations, but complex reasoning tasks typically demand many training examples to learn from. However,…

• Efficient Thought Space Exploration Through Strategic Intervention

  Ziheng Li, Hengyi Cai, Xiaochi Wei, Yuchen Li, Shuaiqiang Wang, Zhi-Hong Deng, Dawei Yin · 3 février 2026

  While large language models (LLMs) demonstrate emerging reasoning capabilities, current inference-time expansion methods incur prohibitive computational costs by exhaustive sampling. Through analyzing decoding trajectories, we observe that most next-token predictions align well with the golden outpu…

• How Understanding Forecast Uncertainty Resolves the Explainability Problem in Machine Learning Models

  Joseph L. Breeden · 3 février 2026

  For applications of machine learning in critical decisions, explainability is a primary concern, and often a regulatory requirement. Local linear methods for generating explanations, such as LIME and SHAP, have been criticized for being unstable near decision boundaries. In this paper, we explain th…

• T-COL: Generating Counterfactual Explanations for General User Preferences on Variable Machine Learning Systems

  Ming Wang, Daling Wang, Wenfang Wu, Shi Feng, Yifei Zhang · 3 février 2026

  To address the interpretability challenge in machine learning (ML) systems, counterfactual explanations (CEs) have emerged as a promising solution. CEs are unique as they provide workable suggestions to users, instead of explaining why a certain outcome was predicted. The application of CEs encounte…

• Augmenting Clinical Decision-Making with an Interactive and Interpretable AI Copilot: A Real-World User Study with Clinicians in Nephrology and Obstetrics

  Yinghao Zhu, Dehao Sui, Zixiang Wang, Xuning Hu, Lei Gu, Yifan Qi, Tianchen Wu, Ling Wang, Yuan Wei, Wen Tang, Zhihan Cui, Yasha Wang, Lequan Yu, Ewen M Harrison, Junyi Gao, Liantao Ma · 3 février 2026

  Clinician skepticism toward opaque AI hinders adoption in high-stakes healthcare. We present AICare, an interactive and interpretable AI copilot for collaborative clinical decision-making. By analyzing longitudinal electronic health records, AICare grounds dynamic risk predictions in scrutable visua…

• GraphNNK -- Graph Classification and Interpretability

  Zeljko Bolevic, Milos Brajovic, Isidora Stankovic, Ljubisa Stankovic · 3 février 2026

  Graph Neural Networks (GNNs) have become a standard approach for learning from graph-structured data. However, their reliance on parametric classifiers (most often linear softmax layers) limits interpretability and sometimes hinders generalization. Recent work on interpolation-based methods, particu…

• shapr: Explaining Machine Learning Models with Conditional Shapley Values in R and Python

  Martin Jullum, Lars Henry Berge Olsen, Jon Lachmann, Annabelle Redelmeier · 3 février 2026

  This paper introduces the shapr R package, a versatile tool for generating Shapley value-based prediction explanations for machine learning and statistical regression models. Moreover, the shaprpy Python library brings the core capabilities of shapr to the Python ecosystem. Shapley values originate …

• PRISM: Festina Lente Proactivity -- Risk-Sensitive, Uncertainty-Aware Deliberation for Proactive Agents

  Yuxuan Fu, Xiaoyu Tan, Teqi Hao, Chen Zhan, Xihe Qiu · 3 février 2026

  Proactive agents must decide not only what to say but also whether and when to intervene. Many current systems rely on brittle heuristics or indiscriminate long reasoning, which offers little control over the benefit-burden tradeoff. We formulate the problem as cost-sensitive selective intervention …

• Position: Explaining Behavioral Shifts in Large Language Models Requires a Comparative Approach

  Martino Ciaperoni, Marzio Di Vece, Luca Pappalardo, Fosca Giannotti, Francesco Giannini · 3 février 2026

  Large-scale foundation models exhibit behavioral shifts: intervention-induced behavioral changes that appear after scaling, fine-tuning, reinforcement learning or in-context learning. While investigating these phenomena have recently received attention, explaining their appearance is still overlooke…