Explainable Artificial Intelligence (XAI)

Derniers papiers

• Hybrid Decision Making via Conformal VLM-generated Guidance

  Debodeep Banerjee, Burcu Sayin, Stefano Teso, Andrea Passerini · 17 avril 2026

  Building on recent advances in AI, hybrid decision making (HDM) holds the promise of improving human decision quality and reducing cognitive load. We work in the context of learning to guide (LtG), a recently proposed HDM framework in which the human is always responsible for the final decision: rat…

• Seeing Through Circuits: Faithful Mechanistic Interpretability for Vision Transformers

  Nina \.Zukowska, Wolfgang Stammer, Bernt Schiele, Jonas Fischer · 17 avril 2026

  Transparency of neural networks' internal reasoning is at the heart of interpretability research, adding to trust, safety, and understanding of these models. The field of mechanistic interpretability has recently focused on studying task-specific computational graphs, defined by connections (edges) …

• Faithfulness Serum: Mitigating the Faithfulness Gap in Textual Explanations of LLM Decisions via Attribution Guidance

  Bar Alon, Itamar Zimerman, Lior Wolf · 17 avril 2026

  Large language models (LLMs) achieve strong performance and have revolutionized NLP, but their lack of explainability keeps them treated as black boxes, limiting their use in domains that demand transparency and trust. A promising direction to address this issue is post-hoc text-based explanations, …

• Simulating Human Cognition: Heartbeat-Driven Autonomous Thinking Activity Scheduling for LLM-based AI systems

  Hong Su · 17 avril 2026

  Large Language Model (LLM) agents have demonstrated remarkable capabilities in reasoning and tool use, yet they often suffer from rigid, reactive control flows that limit their adaptability and efficiency. Most existing frameworks rely on fixed pipelines or failure-triggered reflection, causing agen…

• Mechanistic Decoding of Cognitive Constructs in LLMs

  Yitong Shou, Manhao Guan · 17 avril 2026

  While Large Language Models (LLMs) demonstrate increasingly sophisticated affective capabilities, the internal mechanisms by which they process complex emotions remain unclear. Existing interpretability approaches often treat models as black boxes or focus on coarse-grained basic emotions, leaving t…

• TRACER: Trace-Based Adaptive Cost-Efficient Routing for LLM Classification

  Adam Rida · 17 avril 2026

  Every call to an LLM classification endpoint produces a labeled input-output pair already retained in production logs. These pairs constitute a free, growing training set: a lightweight surrogate trained on them can absorb a significant portion of future traffic at near-zero marginal inference cost.…

• TrigReason: Trigger-Based Collaboration between Small and Large Reasoning Models

  Yi Zhao, Yajuan Peng, Cam-Tu Nguyen, Zuchao Li, Xiaoliang Wang, Xiaoming Fu, Hai Zhao · 17 avril 2026

  Large Reasoning Models (LRMs) achieve strong performance on complex tasks through extended chains of thought but suffer from high inference latency due to autoregressive reasoning. Recent work explores using Small Reasoning Models (SRMs) to accelerate LRM inference. In this paper, we systematically …

• Prompt Optimization Is a Coin Flip: Diagnosing When It Helps in Compound AI Systems

  Xing Zhang, Guanghui Wang, Yanwei Cui, Wei Qiu, Ziyuan Li, Bing Zhu, Peiyang He · 17 avril 2026

  Prompt optimization in compound AI systems is statistically indistinguishable from a coin flip: across 72 optimization runs on Claude Haiku (6 methods $\times$ 4 tasks $\times$ 3 repeats), 49% score below zero-shot; on Amazon Nova Lite, the failure rate is even higher. Yet on one task, all six metho…

• xFODE: An Explainable Fuzzy Additive ODE Framework for System Identification

  Ertugrul Kececi, Tufan Kumbasar · 17 avril 2026

  Recent advances in Deep Learning (DL) have strengthened data-driven System Identification (SysID), with Neural and Fuzzy Ordinary Differential Equation (NODE/FODE) models achieving high accuracy in nonlinear dynamic modeling. Yet, system states in these frameworks are often reconstructed without cle…

• Expert-Guided Class-Conditional Goodness-of-Fit Scores for Interpretable Classification with Informative Missingness: An Application to Seismic Monitoring

  Shahar Cohen, David M. Steinberg, Yael Radzyner, Yochai Ben Horin · 17 avril 2026

  We study a classification problem with three key challenges: pervasive informative missingness, the integration of partial prior expert knowledge into the learning process, and the need for interpretable decision rules. We propose a framework that encodes prior knowledge through an expert-guided cla…

• Towards Verified and Targeted Explanations through Formal Methods

  Hanchen David Wang, Diego Manzanas Lopez, Preston K. Robinette, Ipek Oguz, Taylor T. Johnson, Meiyi Ma · 17 avril 2026

  As deep neural networks are deployed in safety-critical domains such as autonomous driving and medical diagnosis, stakeholders need explanations that are interpretable but also trustworthy with formal guarantees. Existing XAI methods fall short: heuristic attribution techniques (e.g., LIME, Integrat…

• RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography

  M\'elanie Roschewitz, Kenneth Styppa, Yitian Tao, Jiwoong Sohn, Jean-Benoit Delbrouck, Benjamin Gundersen, Nicolas Deperrois, Christian Bluethgen, Julia Vogt, Bjoern Menze, Farhad Nooralahzadeh, Michael Krauthammer, Michael Moor · 17 avril 2026

  Vision-language models (VLM) have markedly advanced AI-driven interpretation and reporting of complex medical imaging, such as computed tomography (CT). Yet, existing methods largely relegate clinicians to passive observers of final outputs, offering no interpretable reasoning trace for them to insp…

• Shapley Value-Guided Adaptive Ensemble Learning for Explainable Financial Fraud Detection with U.S. Regulatory Compliance Validation

  Mohammad Nasir Uddin, Md Munna Aziz · 17 avril 2026

  Financial crime costs U.S. institutions over $32 billion each year. Although AI tools for fraud detection have become more advanced, their use in real-world systems still faces a major obstacle: many of these models operate as black boxes that cannot provide the transparent, auditable explanations r…

• Interpretable and Explainable Surrogate Modeling for Simulations: A State-of-the-Art Survey and Perspectives on Explainable AI for Decision-Making

  Pramudita Satria Palar, Paul Saves, Muhammad Daffa Robani, Nicolas Verstaevel, Moncef Garouani, Julien Aligon, Koji Shimoyama, Joseph Morlier, Benoit Gaudou · 17 avril 2026

  The simulation of complex systems increasingly relies on sophisticated but fundamentally opaque computational black-box simulators. Surrogate models play a central role in reducing the computational cost of complex systems simulations across a wide range of scientific and engineering domains. Notwit…

• Agentic Explainability at Scale: Between Corporate Fears and XAI Needs

  Yomna Elsayed, Cecily Jones · 17 avril 2026

  As companies enter the race for agentic AI adoption, fears surface around agentic autonomy and its subsequent risks. These fears compound as companies scale their agentic AI adoption with low-code applications, without a comparable scaling in their governance processes and expertise resulting in a p…

• Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges

  Xiaohua Wang, Muzhao Tian, Yuqi Zeng, Zisu Huang, Jiakang Yuan, Bowen Chen, Jingwen Xu, Mingbo Zhou, Wenhao Liu, Muling Wu, Zhengkang Guo, Qi Qian, Yifei Wang, Feiran Zhang, Ruicheng Yin, Shihan Dou, Changze Lv, Tao Chen, Kaitao Song, Xu Tan, Tao Gui, Xiaoqing Zheng, Xuanjing Huang · 16 avril 2026

  Reinforcement Learning from Human Feedback (RLHF) and related alignment paradigms have become central to steering large language models (LLMs) and multimodal large language models (MLLMs) toward human-preferred behaviors. However, these approaches introduce a systemic vulnerability: reward hacking, …

• Selecting Feature Interactions for Generalized Additive Models by Distilling Foundation Models

  Jingyun Jia, Chandan Singh, Rich Caruana, Ben Lengerich · 16 avril 2026

  Identifying meaningful feature interactions is a central challenge in building accurate and interpretable models for tabular data. Generalized additive models (GAMs) have shown great success at modeling tabular data, but often rely on heuristic procedures to select interactions, potentially missing …

• C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences

  Akira Kawabata, Saku Sugawara · 16 avril 2026

  Rubric-augmented verification guides reward models with explicit evaluation criteria, yielding more reliable judgments than single-model verification. However, most existing methods require costly rubric annotations, limiting scalability. Moreover, we find that rubric generation is vulnerable to a f…

• Can Cross-Layer Transcoders Replace Vision Transformer Activations? An Interpretable Perspective on Vision

  Gerasimos Chatzoudis, Konstantinos D. Polyzos, Zhuowei Li, Difei Gu, Gemma E. Moran, Hao Wang, Dimitris N. Metaxas · 16 avril 2026

  Understanding the internal activations of Vision Transformers (ViTs) is critical for building interpretable and trustworthy models. While Sparse Autoencoders (SAEs) have been used to extract human-interpretable features, they operate on individual layers and fail to capture the cross-layer computati…

• Bi-Predictability: A Real-Time Signal for Monitoring LLM Interaction Integrity

  Wael Hafez, Amir Nazeri · 16 avril 2026

  Large language models (LLMs) are increasingly deployed in high-stakes autonomous and interactive workflows, where reliability demands continuous, multi-turn coherence. However, current evaluation methods either rely on post-hoc semantic judges, measure unidirectional token confidence (e.g., perplexi…

• Hessian-Enhanced Token Attribution (HETA): Interpreting Autoregressive LLMs

  Vishal Pramanik, Maisha Maliha, Nathaniel D. Bastian, Sumit Kumar Jha · 16 avril 2026

  Attribution methods seek to explain language model predictions by quantifying the contribution of input tokens to generated outputs. However, most existing techniques are designed for encoder-based architectures and rely on linear approximations that fail to capture the causal and semantic complexit…

• UNBOX: Unveiling Black-box visual models with Natural-language

  Simone Carnemolla, Chiara Russo, Simone Palazzo, Quentin Bouniot, Daniela Giordano, Zeynep Akata, Matteo Pennisi, Concetto Spampinato · 16 avril 2026

  Ensuring trustworthiness in open-world visual recognition requires models that are interpretable, fair, and robust to distribution shifts. Yet modern vision systems are increasingly deployed as proprietary black-box APIs, exposing only output probabilities and hiding architecture, parameters, gradie…

• Quantifying and Understanding Uncertainty in Large Reasoning Models

  Yangyi Li, Chenxu Zhao, Mengdi Huai · 16 avril 2026

  Large Reasoning Models (LRMs) have recently demonstrated significant improvements in complex reasoning. While quantifying generation uncertainty in LRMs is crucial, traditional methods are often insufficient because they do not provide finite-sample guarantees for reasoning-answer generation. Confor…

• Med-CAM: Minimal Evidence for Explaining Medical Decision Making

  Pirzada Suhail, Aditya Anand, Amit Sethi · 16 avril 2026

  Reliable and interpretable decision-making is essential in medical imaging, where diagnostic outcomes directly influence patient care. Despite advances in deep learning, most medical AI systems operate as opaque black boxes, providing little insight into why a particular diagnosis was reached. In th…

• ReSS: Learning Reasoning Models for Tabular Data Prediction via Symbolic Scaffold

  Chenlang Yi, Gang Li, Zizhan Xiong, Tue Minh Cao, Yanmin Gong, My T. Thai, Tianbao Yang · 16 avril 2026

  Tabular data remains prevalent in high-stakes domains such as healthcare and finance, where predictive models are expected to provide both high accuracy and faithful, human-understandable reasoning. While symbolic models offer verifiable logic, they lack semantic expressiveness. Meanwhile, general-p…