SOURCE-LINKED INTELLIGENCE

Automated Testing of LLM-Based Post Hoc Explainers Using Model Checking as an Oracle

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Large language models (LLMs) are used as post hoc explainers of sequential decision-making policies, producing natural-language explanations of why an action was chosen. However, LLMs often generate plausible but incorrect statements, and no existing approach systematically tests whether such explanations are faithful to the underlying environment. Two classic software testing challenges stand in the way: there is no oracle for the correctness of an explanation, and the test inputs, natural language queries about a policy's behavior, lack the structure needed for systematic test case generatio

Read original source ↗ Open in workspace

recordType

paper

region

Global