<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hoshino-etal-2026-self">
    <titleInfo>
        <title>Does Self-Consistency Improve the Recall of Encyclopedic Knowledge?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sho</namePart>
        <namePart type="family">Hoshino</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ukyo</namePart>
        <namePart type="family">Honda</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Peinan</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-391-3</identifier>
    </relatedItem>
    <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.</abstract>
    <identifier type="citekey">hoshino-etal-2026-self</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-short.2/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>9</start>
            <end>17</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Does Self-Consistency Improve the Recall of Encyclopedic Knowledge?
%A Hoshino, Sho
%A Honda, Ukyo
%A Zhang, Peinan
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-391-3
%F hoshino-etal-2026-self
%X 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.
%U https://aclanthology.org/2026.acl-short.2/
%P 9-17

Markdown (Informal)

[Does Self-Consistency Improve the Recall of Encyclopedic Knowledge?](https://aclanthology.org/2026.acl-short.2/) (Hoshino et al., ACL 2026)

• Does Self-Consistency Improve the Recall of Encyclopedic Knowledge? (Hoshino et al., ACL 2026)

ACL

• Sho Hoshino, Ukyo Honda, and Peinan Zhang. 2026. Does Self-Consistency Improve the Recall of Encyclopedic Knowledge?. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 9–17, San Diego, California, United States. Association for Computational Linguistics.