Large-scale foundation models exhibit behavioral shifts when subjected to interventions such as scaling, fine-tuning, reinforcement learning with human feedback, or in-context learning. Current explainability methods are structurally ill-suited to explain these shifts, because they either treat models as static objects, as traditional eXplainable AI (XAI) approaches do, or merely compare independent explanations across different checkpoints of a model. As a result, these approaches fail to explain the functional transition between two model instances in which a certain behavior has shifted following an intervention. This gap creates significant governance risks across jurisdictions including the EU AI Act, US state legislation, and Chinese AI regulations, which require documenting causal chains for substantial system modifications. This position paper argues that explaining behavioral shifts in large language models requires a principled approach that treats the shift itself as the primary object of explanation: namely, one that explains how and why an intervention transforms a reference model into an updated model with different behavior. To support this claim, we introduce Comparative XAI (XAI$_Δ$), a novel XAI paradigm aimed at explaining the difference between two model checkpoints where a behavior has shifted, together with a set of desiderata specifying what XAI$_Δ$ explainers and explanations must satisfy, including comparability, validity, actionability, and monitoring, with the goal of grounding model auditing in explicit, measurable requirements. Finally, we provide preliminary evidence suggesting the need for XAI$_Δ$ in practice through illustrative experiments, compiling the resulting findings into a transition report directly usable for governance and incident documentation.
Are LLM Agents Behaviorally Coherent? A Latent Profiling Approach for Social Simulation
Department of Computer Science and Engineering, University of Minnesota（明尼苏达大学计算机科学与工程系）；Department of African American & African Studies, University of Minnesota（明尼苏达大学非裔美国人与非洲研究系）；Department of Sociology, University of Chicago（芝加哥大学社会学系）
Unified Models of Human Behavioral Agents in Bandits, Contextual Bandits and RL
Center for Theoretical Neuroscience, Columbia University（哥伦比亚大学理论神经科学中心）；IBM Thomas J. Watson Research Center（IBM托马斯·J·沃森研究中心）；Mila - Quebec AI Institute, University of Montreal（蒙特利尔大学Mila魁北克人工智能研究所）
SVBRD-LLM: Self-Verifying Behavioral Rule Discovery for Autonomous Vehicle Identification
Fariborz Maseeh Department of Civil, Architectural, and Environmental Engineering, The University of Texas at Austin（德克萨斯大学奥斯汀分校土木、建筑与环境工程学院）；School of Architecture, The University of Texas at Austin（德克萨斯大学奥斯汀分校建筑学院）
TalkToAgent: A Human-centric Explanation of Reinforcement Learning Agents with Large Language Models
Department of Chemical and Biological Engineering, Seoul National University, Republic of Korea（化学与生物工程系，首尔国立大学）；Davidson School of Chemical Engineering, Purdue University, United States（化学工程大卫森学院，普渡大学）
"There Is Not Enough Information": On the Effects of Explanations on Perceptions of Informational Fairness and Trustworthiness in Automated Decision-Making
When Bias Backfires: The Modulatory Role of Counterfactual Explanations on the Adoption of Algorithmic Bias in XAI-Supported Human Decision-Making
Machine Learning Group, Bielefeld University（比勒菲尔德大学机器学习组）；Research Center Trustworthy Data Science and Security of the University Alliance Ruhr, Faculty of Informatics, Technical University Dortmund（鲁尔大学联盟可信数据科学与安全研究所以及多特蒙德技术大学信息学院）
