04:00
2026-07-16
arxiv.org
large-language-models
Interventional Grounding Audits: Black-Box Premise-Dependency Tests for LLM Chain-of-Thought via Predicate Substitution
Researchers introduced interventional grounding audits, a black-box method to test whether LLM chain-of-thought reasoning genuinely depends on its stated premises by substituting predicates. Applied t…