Explainable Artificial Intelligence (XAI)

Derniers papiers

• Using Cognitive Models to Improve Language Model Simulation of Human Persuasion Games

  Zirui Cheng, Zeyu Shen, Thomas L. Griffiths, Peter Henderson · 17 juin 2026

  People make decisions differently in strategic interactions. Some update beliefs like a Bayesian; others exhibit biases like motivated reasoning. Although creators of large language models use simulated humans for safety evaluations and training, they often fail to cover this breadth of human behavi…

• SketchXplain: Intuitive Visual Explanations of Image Classifiers with Sketches

  Wencan Zhang, Mario Michelessa, Xuejun Zhao, Brian Y. Lim · 17 juin 2026

  Saliency map visualizations explain image-based AI predictions by pointing to regions, but these are often unintuitive and semantically unclear, leaving an interpretability gap. We argue that AI explanations should be intuitive -- coherent to user knowledge, yet simple and selective to accelerate in…

• Model Validation of Agentic AI Systems: A POMDP-Based Framework for Belief-State, Forecast, and Policy Validation

  Matthew Francis Dixon · 17 juin 2026

  Agentic artificial intelligence systems introduce a new class of model risk. Unlike traditional predictive models, autonomous agents continuously acquire information, form beliefs regarding latent states of the environment, generate forecasts, select actions, and adapt their behavior over time. Exis…

• Closing the Feedback Loop: From Experience Extraction to Insight Governance in Verbal Reinforcement Learning

  Yanwei Cui, Xing Zhang, Yulong Zhang, Li Shao, Xiaofeng Shi, Guanghui Wang, Peiyang He · 17 juin 2026

  Training-free verbal reinforcement learning enables LLM agents to learn from world feedback -- objective signals such as dynamic task outcomes, market returns, or demand forecasts -- by extracting verbal rules from experience and injecting them as context, updating the agent's behavior without param…

• Small Initialization Matters for Large Language Models

  Liangkai Hang, Junjie Yao, Zhiyu Li, Feiyu Xiong, Hongkang Yang, Zhi-Qin John Xu · 17 juin 2026

  Large language models provide a tractable system for asking how intelligence itself emerges, rather than only how LLMs can be engineered. Although progress is usually attributed to scale, data and architecture, we show that parameter initialization is a gene-like determinant of training and, in part…

• ConTex: Reformulating Counterfactual Generation For Time Series Forecasting

  Jan Voets, Hasan Tercan, Tobias Meisen, Sebastian Baum · 17 juin 2026

  Decision-making with deep learning-based time series forecasting requires not only accurate predictions but also actionable insights. However, current architectures do not inherently provide such information. Specifically, guidance is needed on how current conditions must be modified to shift from a…

• Can LLMs Be CEOs? Benchmarking Strategic Resource Reallocation with Multi-Role Agent Simulation

  Yuyang Dai, Xueqing Peng, Lingfei Qian, Zhuohan Xie · 17 juin 2026

  Evaluating the decision-making capabilities of large language models (LLMs) is a growing research priority, yet existing benchmarks focus on isolated cognitive tasks such as reasoning, knowledge retrieval, and economic rationality in stylized settings. These evaluations overlook the defining challen…

• CausalT5k: Diagnosing Refusal and Failure Modes in Trustworthy Causal Reasoning Across Causal Rungs

  Longling Geng, Andy Ouyang, Theodore Wu, Daphne Barretto, Matthew John Hayes, Rachael Cooper, Yuqiao Zeng, Sameer Vijay, Gia Ancone, Ankit Rai, Matthew Wolfman, Patrick Flanagan, Edward Y. Chang · 17 juin 2026

  Large language models increasingly produce fluent causal explanations, yet they often fail in ways aggregate accuracy cannot diagnose: confusing association with intervention, abandoning correct judgments under pressure, over-refusing valid claims, or answering when evidence is underdetermined. We i…

• Know Thy Reasoner: Not All Language Models Explore Alike

  Moulik Choraria, Argyrios Gerogiannis, Anirban Das, Supriyo Chakraborty, Sourya Basu, Sambit Sahu, Lav R. Varshney · 17 juin 2026

  Compute scaling for LLM reasoning trades off exploring solution approaches (\emph{breadth}) against refining promising ones (\emph{depth}), yet why a given trade-off works, and why it often fails to transfer across models, remains unclear. We argue that \textbf{the optimal strategy depends on the mo…

• The limits of interpretability in multiple linear regression

  Anand Sharma, Chen Liu, Daniele Coslovich, Misaki Ozawa · 16 juin 2026

  Interpreting machine-learning models has attracted increasing attention, particularly in the physical sciences, where one often seeks to understand the underlying mechanisms rather than merely make predictions. Multiple linear regression is often regarded as an interpretable alternative to more comp…

• Tail-Shape Estimation in LLM Evaluation Is Fragile: A Protocol for Diagnosing False Positives

  Luca Zhou · 16 juin 2026

  Recent work motivates moving large language model (LLM) evaluation from mean-based to tail-aware metrics, including conditional value-at-risk and tail-index estimates of reward-model error. We ask whether the canonical extreme-value-theory tail-index parameter, which isolates how heavy a tail is fro…

• Scalable and Interpretable Representation Alignment with Ordinal Similarity

  Diogo Soares, Pankhil Gawade, Andrea Dittadi, Ewa Szczurek · 16 juin 2026

  Evaluating representation similarity is fundamental to representation learning. However, existing metrics suffer from significant limitations: they lack interpretability due to shifting baselines, lack robustness to outliers, and are computationally intractable for large datasets, forcing reliance o…

• PromptShift-CRC: Drift-Aware Conformal Risk Control for Foundation Models Under Prompt and Domain Shift

  Jeffery Opoku, David Banahene · 16 juin 2026

  Foundation models are now used in settings where the prompts they receive can change quickly. Users change, topics change, policies change, and the model may suddenly face a kind of request that was rare in the calibration data. This makes fixed calibration risky. Conformal prediction and conformal …

• We Need Explanation Cards to Connect Explanation Algorithms to the Real World

  Eric G\"unther, Bal\'azs Szabados, Kristof Meding, Gunnar K\"onig, Sebastian Bordt, Ulrike von Luxburg · 16 juin 2026

  Algorithmic explanations are intended to help stakeholders understand opaque algorithmic decisions, but in practice, they often fall short. First, the meaning of algorithmic explanations is often not what one might intuitively expect, so expert knowledge is required to interpret them correctly. Seco…

• Assessing Reliability of Symbol Detection in Concept Bottleneck Models

  Javier Fumanal-Idocin, Javier Andreu-Perez · 16 juin 2026

  Concept Bottleneck Models (CBMs) are a relevant tool for explainable Artificial Intelligence because they make their predictions through human-interpretable symbols. However, high task accuracy does not guarantee that these symbols are detected faithfully: jointly trained CBMs may encode task-specif…

• RecourseBench: A Modular Framework for Reproducible Algorithmic Recourse Evaluation

  Zahra Khotanlou, Hashir Ahmed, Chenghao Tan, Ahmed Abdelaal, Amir-Hossein Karimi · 16 juin 2026

  Algorithmic recourse methods provide counterfactual explanations that inform individuals of the actions required to overturn an unfavorable model decision. Despite rapid methodological progress, principled comparison remains elusive; existing frameworks are often difficult to extend and lack both in…

• Scalable Circuit Learning for Interpreting Large Language Models

  Naiyu Yin, Dennis Wei, Tian Gao, Amit Dhurandhar, Karthikeyan Natesan Ramamurthy, Yue Yu · 16 juin 2026

  A prominent research direction in mechanistic interpretability is learning sparse circuits over LLM components to reveal how they jointly produce model behavior. However, raw neurons are polysemantic, making learned circuits hard to interpret. Sparse autoencoder (SAE) features alleviate this, but th…

• How Should World Models Be Evaluated? A Decision-Making-Centric Position

  Yang Yu, Shiyuan Zhang, Yifei Sheng, Haoxiang Ren, Haoxin Lin · 16 juin 2026

  World models have rapidly become one of the central abstractions in modern AI. Yet the term now refers to several different objects: action-conditioned environment models, latent imagination models, future-video predictors, interactive neural simulators, latent predictive representations, and synthe…

• LLM Judges Have Dark Current: A Psychometric Datasheet for LLM-as-a-Judge Evaluation

  Hiroyasu Usami, Keisuke Hara, Ayato Tsuboi, Naohiko Matsuda · 16 juin 2026

  LLM-as-a-judge systems are now routinely used for open-ended model evaluation, where human preference annotation is costly, slow, and difficult to reproduce. Yet these judges are often reported as scalar accuracy, win-rate, or agreement devices. We argue that a judge should instead be reported as a …

• Visualizing Uncertainty: Spatial Maps of Missing and Conflicting Evidence in Deep Learning

  Dong Hyun Jeong, Feng Chen, Jin-Hee Cho, Lance M. Kaplan, Audun J{\o}sang, Soo-Yeon Ji · 16 juin 2026

  Understanding when and why deep neural networks are uncertain is crucial for deploying reliable machine learning systems in safety-critical domains. While existing uncertainty quantification methods provide scalar measures of model confidence, they offer limited insight into which spatial regions of…

• XAI-Grounded Explanation Generation for Speech Deepfake Detection with Training-Free Multimodal Large Language Models

  Yupei Li, Qiyang Sun, Xiaoliang Wu, Chenxi Wang, Berrak Sisman, Bj\"orn W. Schuller · 16 juin 2026

  Speech deepfake detection (SDD) systems require trustworthy explanations for reliable decision-making. Existing explanation ways mainly fall into two categories. Traditional explainable AI (XAI), such as gradient-based attribution, produces low-level attribution signals tightly coupled with model de…

• VeriGraph: Towards Verifiable Data-Analytic Agents

  Jiajie Jin, Zhao Yang, Wenle Liao, Yuyang Hu, Guanting Dong, Xiaoxi Li, Yutao Zhu, Zhicheng Dou · 16 juin 2026

  LLM-based agents have demonstrated strong capabilities in data-intensive analytical tasks, yet their outputs are rarely verifiable: a reliance on linear text trajectories makes their reasoning difficult to audit. In particular, deterministic computations over raw data and semantic deductions over na…

• Disentangling Hallucinations: Orthogonal Semantic Projection for Robust Interpretability

  Emirhan Bilgi\c{c}, Baptiste Caramiaux, Zhi Yan, Gianni Franchi · 16 juin 2026

  As Vision-Language Models are increasingly deployed in safety-critical applications, the trustworthiness of their explanations becomes crucial. Explainable AI (XAI) methods for Vision-Language Models often suffer from semantic hallucination, where attribution maps highlight prominent image regions e…

• Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning

  Ali Dasdan, Manan Shah, W. Russell Neuman, Chad Coleman, Kund Meghani, Safinah Ali · 16 juin 2026

  Behavioral audits of Large Language Models on moral prompts measure what the model says, not the internal computation producing it. We use Transluce, an AI-driven mechanistic-interpretability platform, to examine LLaMA 3.1-8B-Instruct on 54 moral prompts in four batteries: 17 dilemmas, policy, and m…

• Beyond Accuracy: Measuring Bias Acknowledgment in Chain-of-Thought Reasoning for Responsible AI Evaluation

  Xian Sun, Wei Gao, Yingshuo Wang, Lingdong Kong, Yanhang Li, Zhichao Fan, Zexin Zhuang, Wenlong Dong, Zhiyuan Zheng, Hrishikesh Paranjape, Abhishek Mandal, Johnny R. Zhang · 16 juin 2026

  Reasoning models are increasingly used in settings where the final answer is not the only object of review: educational tools may show students intermediate steps, decision-support systems may require human oversight, and audit workflows may inspect traces for misleading or biased input. In such set…