@inproceedings{hashimoto-etal-2025-decoding,
    title = "Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Models",
    author = "Hashimoto, Wataru  and
      Kamigaito, Hidetaka  and
      Watanabe, Taro",
    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.788/",
    doi = "10.18653/v1/2025.findings-emnlp.788",
    pages = "14601--14613",
    ISBN = "979-8-89176-335-7",
    abstract = "Decoding strategies manipulate the probability distribution underlying the output of a language model and can therefore affect both generation quality and its uncertainty. In this study, we investigate the impact of decoding strategies on uncertainty estimation in Large Language Models (LLMs). Our experiments show that Contrastive Search, which mitigates repetition, yields better uncertainty estimates on average across a range of preference-aligned LLMs. In contrast, the benefits of these strategies sometimes diverge when the model is only post-trained with supervised fine-tuning, i.e. without explicit alignment."
}