<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saparkhan-etal-2026-self">
    <titleInfo>
        <title>Self-Consistency from Only Two Samples: CoT–PoT Ensembling for Efficient LLM Reasoning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Raman</namePart>
        <namePart type="family">Saparkhan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Majd</namePart>
        <namePart type="family">Hawasly</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Md</namePart>
        <namePart type="given">Rizwan</namePart>
        <namePart type="family">Parvez</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mohammad</namePart>
        <namePart type="family">Raza</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>Findings of the Association for Computational Linguistics: ACL 2026</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">979-8-89176-395-1</identifier>
    </relatedItem>
    <abstract>Self-consistency (SC) is a popular technique for improving the reasoning accuracy of large language models by aggregating multiple sampled outputs, but it comes at a high computational cost due to extensive sampling. We introduce a hybrid ensembling approach that leverages the complementary strengths of two distinct modes of reasoning: Chain-of-Thought (CoT) and Program-of-Thought (PoT). We describe a general framework for combining these two forms of reasoning in self-consistency, as well as particular strategies for both full sampling and early-stopping. We show that CoT-PoT ensembling not only improves overall accuracy, but also drastically reduces the number of samples required for SC by a factor of 9.3x. In particular, the majority of tasks (78.6%) can be addressed with only two samples, which has not been possible with any prior SC methods.</abstract>
    <identifier type="citekey">saparkhan-etal-2026-self</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-acl.1642/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>32804</start>
            <end>32839</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Self-Consistency from Only Two Samples: CoT–PoT Ensembling for Efficient LLM Reasoning
%A Saparkhan, Raman
%A Hawasly, Majd
%A Parvez, Md Rizwan
%A Raza, Mohammad
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F saparkhan-etal-2026-self
%X Self-consistency (SC) is a popular technique for improving the reasoning accuracy of large language models by aggregating multiple sampled outputs, but it comes at a high computational cost due to extensive sampling. We introduce a hybrid ensembling approach that leverages the complementary strengths of two distinct modes of reasoning: Chain-of-Thought (CoT) and Program-of-Thought (PoT). We describe a general framework for combining these two forms of reasoning in self-consistency, as well as particular strategies for both full sampling and early-stopping. We show that CoT-PoT ensembling not only improves overall accuracy, but also drastically reduces the number of samples required for SC by a factor of 9.3x. In particular, the majority of tasks (78.6%) can be addressed with only two samples, which has not been possible with any prior SC methods.
%U https://aclanthology.org/2026.findings-acl.1642/
%P 32804-32839

Markdown (Informal)

[Self-Consistency from Only Two Samples: CoT–PoT Ensembling for Efficient LLM Reasoning](https://aclanthology.org/2026.findings-acl.1642/) (Saparkhan et al., Findings 2026)

• Self-Consistency from Only Two Samples: CoT–PoT Ensembling for Efficient LLM Reasoning (Saparkhan et al., Findings 2026)

ACL

• Raman Saparkhan, Majd Hawasly, Md Rizwan Parvez, and Mohammad Raza. 2026. Self-Consistency from Only Two Samples: CoT–PoT Ensembling for Efficient LLM Reasoning. In Findings of the Association for Computational Linguistics: ACL 2026, pages 32804–32839, San Diego, California, United States. Association for Computational Linguistics.