LM vs LM: Detecting Factual Errors via Cross Examination
Submission Type: Regular Long Paper
Submission Track: Question Answering
Submission Track 2: Theme Track: Large Language Models and the Future of NLP
Keywords: knowledge, factuality, LLM, question answering, interpretability, interactivity, multi-agent, consistency, fact checking, dialogue
Abstract: A prominent weakness of modern language models (LMs) is their tendency to generate factually incorrect text, which hinders their usability. A natural question is whether such factual errors can be detected automatically. Inspired by truth-seeking mechanisms in law, we propose a factuality evaluation framework for LMs that is based on cross-examination. Our key idea is that an incorrect claim is likely to result in inconsistency with other claims that the model generates. To discover such inconsistencies, we facilitate a multi-turn interaction between the LM that generated the claim and another LM (acting as an examiner) which introduces questions to discover inconsistencies. We empirically evaluate our method on factual claims made by multiple recent LMs on four benchmarks, finding that it outperforms existing methods and baselines, often by a large gap. Our results demonstrate the potential of using interacting LMs for capturing factual errors.
Submission Number: 2117
Loading