@inproceedings{feng-etal-2025-rethinking,
    title = "Rethinking {LLM} Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertainty",
    author = "Feng, Yu  and
      Htut, Phu Mon  and
      Qi, Zheng  and
      Xiao, Wei  and
      Mager, Manuel  and
      Pappas, Nikolaos  and
      Halder, Kishaloy  and
      Li, Yang  and
      Benajiba, Yassine  and
      Roth, Dan",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.660/",
    doi = "10.18653/v1/2025.findings-emnlp.660",
    pages = "12349--12375",
    ISBN = "979-8-89176-335-7",
    abstract = "Quantifying uncertainty in black-box LLMs is vital for reliable responses and scalable oversight. Existing methods, which gauge a model{'}s uncertainty through evaluating self-consistency in responses to the target query, can be misleading: an LLM may confidently provide an incorrect answer to a target query, yet give a confident and accurate answer to that same target query when answering a knowledge-preserving perturbation of the query. We systematically analyze the model behaviors and demonstrate that this discrepancy stems from suboptimal retrieval of parametric knowledge, often due to contextual biases that prevent consistent access to stored knowledge. We then introduce DiverseAgentEntropy, a novel, theoretically-grounded method employing multi-agent interaction across diverse query variations for uncertainty estimation of black-box LLMs. This approach more accurately assesses an LLM{'}s true uncertainty and improves hallucination detection, outperforming existing self-consistency based techniques."
}