Explainable Artificial Intelligence (XAI)

Derniers papiers

• An Optimized Decision Tree-Based Framework for Explainable IoT Anomaly Detection

  Ashikuzzaman, Md. Shawkat Hossain, Jubayer Abdullah Joy, Md Zahid Akon, Md Manjur Ahmed, Md. Naimul Islam · 22 janvier 2026

  The increase in the number of Internet of Things (IoT) devices has tremendously increased the attack surface of cyber threats thus making a strong intrusion detection system (IDS) with a clear explanation of the process essential towards resource-constrained environments. Nevertheless, current IoT I…

• Counterfactual Modeling with Fine-Tuned LLMs for Health Intervention Design and Sensor Data Augmentation

  Shovito Barua Soumma, Asiful Arefeen, Stephanie M. Carpenter, Melanie Hingle, Hassan Ghasemzadeh · 22 janvier 2026

  Counterfactual explanations (CFEs) provide human-centric interpretability by identifying the minimal, actionable changes required to alter a machine learning model's prediction. Therefore, CFs can be used as (i) interventions for abnormality prevention and (ii) augmented data for training robust mod…

• Obscuring Data Contamination Through Translation: Evidence from Arabic Corpora

  Chaymaa Abbas, Nour Shamaa, Mariette Awad · 22 janvier 2026

  Data contamination undermines the validity of Large Language Model evaluation by enabling models to rely on memorized benchmark content rather than true generalization. While prior work has proposed contamination detection methods, these approaches are largely limited to English benchmarks, leaving …

• Anytime Optimal Decision Tree Learning with Continuous Features

  Harold Kiossou, Pierre Schaus, Siegfried Nijssen · 22 janvier 2026

  In recent years, significant progress has been made on algorithms for learning optimal decision trees, primarily in the context of binary features. Extending these methods to continuous features remains substantially more challenging due to the large number of potential splits for each feature. Rece…

• Emergent, not Immanent: A Baradian Reading of Explainable AI

  Fabio Morreale, Joan Serr\`a, Yuki Mistufuji · 22 janvier 2026

  Explainable AI (XAI) is frequently positioned as a technical problem of revealing the inner workings of an AI model. This position is affected by unexamined onto-epistemological assumptions: meaning is treated as immanent to the model, the explainer is positioned outside the system, and a causal str…

• Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation

  Muhammad Khalifa, Lajanugen Logeswaran, Jaekyeom Kim, Sungryull Sohn, Yunxiang Zhang, Moontae Lee, Hao Peng, Lu Wang, Honglak Lee · 22 janvier 2026

  Large language models (LLMs) are increasingly used as judges to evaluate agent performance, particularly in non-verifiable settings where judgments rely on agent trajectories including chain-of-thought (CoT) reasoning. This paradigm implicitly assumes that the agent's CoT faithfully reflects both it…

• The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution

  Chen Qian, Peng Wang, Dongrui Liu, Junyao Yang, Dadi Guo, Ling Tang, Jilin Mei, Qihan Ren, Shuai Shao, Yong Liu, Jie Fu, Jing Shao, Xia Hu · 22 janvier 2026

  Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering. As these systems become more autonomous and are deployed at scale, understanding why an agent takes a particular action becomes increasingly importan…

• What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study

  Keyu Lv, Manyi Zhang, Xiaobo Xia, Jingchen Ni, Shannan Yan, Xianzhi Yu, Lu Hou, Chun Yuan, Haoli Bai · 22 janvier 2026

  Reasoning models excel at complex tasks such as coding and mathematics, yet their inference is often slow and token-inefficient. To improve the inference efficiency, post-training quantization (PTQ) usually comes with the cost of large accuracy drops, especially for reasoning tasks under low-bit set…

• GECOBench: A Gender-Controlled Text Dataset and Benchmark for Quantifying Biases in Explanations

  Rick Wilming, Artur Dox, Hjalmar Schulz, Marta Oliveira, Benedict Clark, Stefan Haufe · 22 janvier 2026

  Large pre-trained language models have become a crucial backbone for many downstream tasks in natural language processing (NLP), and while they are trained on a plethora of data containing a variety of biases, such as gender biases, it has been shown that they can also inherit such biases in their w…

• ConceptCaps -- a Distilled Concept Dataset for Interpretability in Music Models

  Bruno Sienkiewicz, {\L}ukasz Neumann, Mateusz Modrzejewski · 21 janvier 2026

  Concept-based interpretability methods like TCAV require clean, well-separated positive and negative examples for each concept. Existing music datasets lack this structure: tags are sparse, noisy, or ill-defined. We introduce ConceptCaps, a dataset of 23k music-caption-audio triplets with explicit l…

• \textit{FocaLogic}: Logic-Based Interpretation of Visual Model Decisions

  Chenchen Zhao, Muxi Chen, Qiang Xu · 21 janvier 2026

  Interpretability of modern visual models is crucial, particularly in high-stakes applications. However, existing interpretability methods typically suffer from either reliance on white-box model access or insufficient quantitative rigor. To address these limitations, we introduce FocaLogic, a novel …

• Incentivizing In-depth Reasoning over Long Contexts with Process Advantage Shaping

  Miao Peng, Weizhou Shen, Nuo Chen, Chenliang Li, Ming Yan, Jia Li · 21 janvier 2026

  Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective in enhancing LLMs short-context reasoning, but its performance degrades in long-context scenarios that require both precise grounding and robust long-range reasoning. We identify the "almost-there" phenomenon in long-context …

• Explanation Multiplicity in SHAP: Characterization and Assessment

  Hyunseung Hwang, Seungeun Lee, Lucas Rosenblatt, Julia Stoyanovich, Steven Euijong Whang · 21 janvier 2026

  Post-hoc explanations are widely used to justify, contest, and audit automated decisions in high-stakes domains. SHAP, in particular, is often treated as a reliable account of which features drove an individual prediction. Yet SHAP explanations can vary substantially across repeated runs even when t…

• Bounded Minds, Generative Machines: Envisioning Conversational AI that Works with Human Heuristics and Reduces Bias Risk

  Jiqun Liu · 21 janvier 2026

  Conversational AI is rapidly becoming a primary interface for information seeking and decision making, yet most systems still assume idealized users. In practice, human reasoning is bounded by limited attention, uneven knowledge, and reliance on heuristics that are adaptive but bias-prone. This arti…

• From Prototypes to Sparse ECG Explanations: SHAP-Driven Counterfactuals for Multivariate Time-Series Multi-class Classification

  Maciej Mozolewski, Bet\"ul Bayrak, Kerstin Bach, Grzegorz J. Nalepa · 21 janvier 2026

  In eXplainable Artificial Intelligence (XAI), instance-based explanations for time series have gained increasing attention due to their potential for actionable and interpretable insights in domains such as healthcare. Addressing the challenges of explainability of state-of-the-art models, we propos…

• Toward Faithful Explanations in Acoustic Anomaly Detection

  Maab Elrashid, Anthony Desch\^enes, Cem Subakan, Mirco Ravanelli, R\'emi Georges, Michael Morin · 21 janvier 2026

  Interpretability is essential for user trust in real-world anomaly detection applications. However, deep learning models, despite their strong performance, often lack transparency. In this work, we study the interpretability of autoencoder-based models for audio anomaly detection, by comparing a sta…

• POLARIS: Typed Planning and Governed Execution for Agentic AI in Back-Office Automation

  Zahra Moslemi, Keerthi Koneru, Yen-Ting Lee, Sheethal Kumar, Ramesh Radhakrishnan · 21 janvier 2026

  Enterprise back office workflows require agentic systems that are auditable, policy-aligned, and operationally predictable, capabilities that generic multi-agent setups often fail to deliver. We present POLARIS (Policy-Aware LLM Agentic Reasoning for Integrated Systems), a governed orchestration fra…

• Balanced Accuracy: The Right Metric for Evaluating LLM Judges -- Explained through Youden's J statistic

  Stephane Collot, Colin Fraser, Justin Zhao, William F. Shen, Timon Willi, Ilias Leontiadis · 21 janvier 2026

  Rigorous evaluation of large language models (LLMs) relies on comparing models by the prevalence of desirable or undesirable behaviors, such as task pass rates or policy violations. These prevalence estimates are produced by a classifier, either an LLM-as-a-judge or human annotators, making the choi…

• Large Language Model for OWL Proofs

  Hui Yang, Jiaoyan Chen, Uli Sattler · 21 janvier 2026

  The ability of Large Language Models (LLMs) to perform reasoning tasks such as deduction has been widely investigated in recent years. Yet, their capacity to generate proofs-faithful, human-readable explanations of why conclusions follow-remains largely under explored. In this work, we study proof g…

• Post-Training as Reweighting: A Stochastic View of Reasoning Trajectories in Language Models

  Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Bo Xue, Qingfu Zhang, Hau-San Wong, Taiji Suzuki · 21 janvier 2026

  Foundation models encode rich structural knowledge but often rely on post-training procedures to adapt their reasoning behavior to specific tasks. Popular approaches such as reinforcement learning with verifiable rewards (RLVR) and inference-time reward aggregation are typically analyzed from a perf…

• Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models

  Junhao Liu, Haonan Yu, Zhenyu Yan, Xin Zhang · 21 janvier 2026

  Post-hoc explanations provide transparency and are essential for guiding model optimization, such as prompt engineering and data sanitation. However, applying model-agnostic techniques to Large Language Models (LLMs) is hindered by prohibitive computational costs, rendering these tools dormant for r…

• Reasoning Stabilization Point: A Training-Time Signal for Stable Evidence and Shortcut Reliance

  Sahil Rajesh Dhayalkar · 21 janvier 2026

  Fine-tuning pretrained language models can improve task performance while subtly altering the evidence a model relies on. We propose a training-time interpretability view that tracks token-level attributions across finetuning epochs. We define explanation driftas the epoch-to-epoch change in normali…

• Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

  Mike A. Merrill, Alexander G. Shaw, Nicholas Carlini, Boxuan Li, Harsh Raj, Ivan Bercovich, Lin Shi, Jeong Yeon Shin, Thomas Walshe, E. Kelly Buchanan, Junhong Shen, Guanghao Ye, Haowei Lin, Jason Poulos, Maoyu Wang, Marianna Nezhurina, Jenia Jitsev, Di Lu, Orfeas Menis Mastromichalakis, Zhiwei Xu, Zizhao Chen, Yue Liu, Robert Zhang, Leon Liangyu Chen, Anurag Kashyap, Jan-Lucas Uslu, Jeffrey Li, Jianbo Wu, Minghao Yan, Song Bian, Vedang Sharma, Ke Sun, Steven Dillmann, Akshay Anand, Andrew Lanpouthakoun, Bardia Koopah, Changran Hu, Etash Guha, Gabriel H. S. Dreiman, Jiacheng Zhu, Karl Krauth, Li Zhong, Niklas Muennighoff, Robert Amanfu, Shangyin Tan, Shreyas Pimpalgaonkar, Tushar Aggarwal, Xiangning Lin, Xin Lan, Xuandong Zhao, Yiqing Liang, Yuanli Wang, Zilong Wang, Changzhi Zhou, David Heineman, Hange Liu, Harsh Trivedi, John Yang, Junhong Lin, Manish Shetty, Michael Yang, Nabil Omi, Negin Raoof, Shanda Li, Terry Yue Zhuo, Wuwei Lin, Yiwei Dai, Yuxin Wang, Wenhao Chai, Shang Zhou, Dariush Wahdany, Ziyu She, Jiaming Hu, Zhikang Dong, Yuxuan Zhu, Sasha Cui, Ahson Saiyed, Arinbj\"orn Kolbeinsson, Jesse Hu, Christopher Michael Rytting, Ryan Marten, Yixin Wang, Alex Dimakis, Andy Konwinski, Ludwig Schmidt · 21 janvier 2026

  AI agents may soon become capable of autonomously completing valuable, long-horizon tasks in diverse domains. Current benchmarks either do not measure real-world tasks, or are not sufficiently difficult to meaningfully measure frontier models. To this end, we present Terminal-Bench 2.0: a carefully …

• SL-CBM: Enhancing Concept Bottleneck Models with Semantic Locality for Better Interpretability

  Hanwei Zhang, Luo Cheng, Rui Wen, Yang Zhang, Lijun Zhang, Holger Hermanns · 21 janvier 2026

  Explainable AI (XAI) is crucial for building transparent and trustworthy machine learning systems, especially in high-stakes domains. Concept Bottleneck Models (CBMs) have emerged as a promising ante-hoc approach that provides interpretable, concept-level explanations by explicitly modeling human-un…

• Actionable Interpretability Must Be Defined in Terms of Symmetries

  Pietro Barbiero, Mateo Espinosa Zarlenga, Francesco Giannini, Alberto Termine, Filippo Bonchi, Mateja Jamnik, Giuseppe Marra · 21 janvier 2026

  This paper argues that interpretability research in Artificial Intelligence is fundamentally ill-posed as existing definitions of interpretability are not *actionable*: they fail to provide formal principles from which concrete modelling and inferential rules can be derived. We posit that for a defi…