DiverseAgentEntropy: Quantifying Black-Box LLM Uncertainty through Diverse Perspectives and Multi-Agent Interaction

Yu Feng, Phu Mon Htut, Zheng Qi, Wei Xiao, Manuel Mager, Nikolaos Pappas, Kishaloy Halder, Yang Li, Yassine Benajiba, Dan Roth

Keywords: Large language Model, Hallucination Detection, Uncertainty Quantification, MultiAgent Interaction

Abstract: Quantifying the uncertainty in the factual parametric knowledge of Large Language Models (LLMs), especially in a black-box setting, poses a significant challenge. Existing methods, which gauge a model’s uncertainty through evaluating self-consistency in responses to the original query, do not always capture true uncertainty. Models might respond consistently to the origin query with a wrong answer, yet respond correctly to varied questions from different perspectives about the same query, and vice versa. In this paper, we propose a novel method, DiverseAgentEntropy, for evaluating a model's uncertainty using multi-agent interaction under the assumption that if a model is certain, it should consistently recall the answer to the original query across a diverse collection of questions about the same original query. We further implement an abstention policy to withhold responses when uncertainty is high. Our method offers a more accurate prediction of the model's reliability and further detects hallucinations, outperforming other self-consistency-based methods. Additionally, it demonstrates that existing models often fail to consistently retrieve the correct answer to the same query under diverse varied questions even when knowing the correct answer.

Primary Area: applications to computer vision, audio, language, and other modalities

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 11694