cs.AIFeb 2, 2026

Comparing Explanations is Not Enough, Explain the Change: New Standards are Needed to Explain Behavioral Shifts in Large Language Models

Authors: Martino Ciaperoni, Marzio Di Vece, Roberto Pellungrini, Luca Pappalardo, Fosca Giannotti, Francesco Giannini

Organizations: Scuola Normale Superiore Pisa, Italy · ISTI-CNR, Italy Pisa, Italy · University of Pisa Pisa, Italy

Abstract

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 (XAIΔ_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 XAIΔ_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 XAIΔ_Δ in practice through illustrative experiments, compiling the resulting findings into a transition report directly usable for governance and incident documentation.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Automatically Finding and Validating Unexpected Side-Effects of Interventions on Language Models

    May 6, 2026Quintin Pope, Ajay Hayagreeve Balaji, Jacques Thibodeau +1Language Model Generation EvaluationLLM Auditing

  2. Fundamental Limitation in Explaining AI

    May 23, 2026Atsushi Suzuki, Jing WangExplainable Artificial Intelligence

  3. From Plausible to Actionable: A Position on LLM Self-Explanations

    Jul 17, 2026Elize Herrewijnen, Benedetta Muscato, Gizem Gezici +1CoT FaithfulnessFaithfulness of Language Model Explanations