Cross-Examiner: Evaluating Consistency of Large Language Model-Generated Explanations

Abstract: LLMs are often asked to explain their outputs to enhance accuracy and transparency. However, evidence suggests that these explanations can misrepresent the models' true reasoning processes. One effective way to identify inaccuracies or omissions in these explanations is through consistency checking, which typically involves asking follow-up questions. This paper introduces, cross-examiner, a new method for generating follow-up questions based on a model's explanation of an initial question. Our method combines symbolic information extraction with LLM-driven question generation, resulting in better follow-up questions than those produced by LLMs alone. Additionally, this approach is more flexible than other methods and can generate a wider variety of follow-up questions.