@inproceedings{wang-etal-2024-soft,
    title = "Soft Self-Consistency Improves Language Models Agents",
    author = "Wang, Han  and
      Prasad, Archiki  and
      Stengel-Eskin, Elias  and
      Bansal, Mohit",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Add-Cong-Liu-Florida-Atlantic-University-author-id/2024.acl-short.28/",
    doi = "10.18653/v1/2024.acl-short.28",
    pages = "287--301",
    abstract = "Generations from large language models (LLMs) can be improved by sampling and scoring multiple solutions to select a final answer. Current {\textquotedblleft}sample and select{\textquotedblright} methods such as self-consistency (SC) rely on majority voting to score answers. However, when tasks have many distinct and valid answers, selection by voting requires a large number of samples. This makes SC prohibitively expensive for interactive tasks that involve generating multiple actions (answers) sequentially. After establishing that majority voting fails to provide consistent gains on such tasks, we demonstrate how to increase success rates by softening the scoring criterion. We introduce Soft Self-Consistency (SOFT-SC), which replaces SC`s discontinuous scoring with a continuous score computed from model likelihoods, allowing for selection even when actions are sparsely distributed. SOFT-SC improves both performance and efficiency on long-horizon interactive tasks, requiring half as many samples as SC for comparable or better performance. For a fixed number of samples, SOFT-SC leads to a 1.3{\%} increase over SC in absolute success rate on writing bash programs, a 6.6{\%} increase on online shopping (WebShop), and a 4.7{\%} increase for an interactive household game (ALFWorld). Finally, we show that SOFT-SC can be applied to both open-source and black-box models."
}