Interventional Grounding Audits: Black-Box Premise-Dependency Tests for LLM Chain-of-Thought via Predicate Substitution
介入式基础审计：通过谓词替换对大语言模型思维链进行黑盒前提依赖性测试
AI总结 研究大语言模型思维链前提依赖性问题，提出介入式基础审计方法，通过谓词替换干预前提并重新运行模型，在ProntoQA基准测试中检测前提依赖性表现优异，还发现了“正确答案，错误推理”信号。
Comments Accepted at the ICLR 2026 Workshop on Logical Reasoning of Large Language Models (https://iclr.cc/virtual/2026/10017466)
