@inproceedings{hoshino-etal-2026-self,
    title = "Does Self-Consistency Improve the Recall of Encyclopedic Knowledge?",
    author = "Hoshino, Sho  and
      Honda, Ukyo  and
      Zhang, Peinan",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-short.2/",
    pages = "9--17",
    ISBN = "979-8-89176-391-3",
    abstract = "While self-consistency is known to improve performance on symbolic reasoning, its effect on the recall of encyclopedic knowledge is unclear due to a lack of targeted evaluation grounds.To address this, we establish such a knowledge recall split for the popular MMLU benchmark by applying a data-driven heuristic from prior work.We validate this split by showing that the performance patterns on the symbolic reasoning and knowledge recall subsets mirror those of GSM8K and MedMCQA, respectively.Using this solid ground, we find that self-consistency consistently improves performance across both symbolic reasoning and knowledge recall, even though its underlying CoT prompting is primarily effective for symbolic reasoning.As a result, we achieve an 89{\%} accuracy on MMLU, the best performance to date with the use of GPT-4o."
}