<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aggarwal-etal-2023-lets">
    <titleInfo>
        <title>Let’s Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pranjal</namePart>
        <namePart type="family">Aggarwal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aman</namePart>
        <namePart type="family">Madaan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yiming</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name>
        <namePart>Mausam</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>A popular approach for improving the correctness of output from large language models (LLMs) is Self-Consistency - poll the LLM multiple times and output the most frequent solution. Existing Self-Consistency techniques always generate a constant number of samples per question, where a better approach will be to non-uniformly distribute the available budget based on the amount of agreement in the samples generated so far. In response, we introduce Adaptive-Consistency, a cost-efficient, model-agnostic technique that dynamically adjusts the number of samples per question using a lightweight stopping criterion. Our experiments over 17 reasoning and code generation datasets and three LLMs demonstrate that Adaptive-Consistency reduces sample budget by up to 7.9 times with an average accuracy drop of less than 0.1%</abstract>
    <identifier type="citekey">aggarwal-etal-2023-lets</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-main.761</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-main.761</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>12375</start>
            <end>12396</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Let’s Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs
%A Aggarwal, Pranjal
%A Madaan, Aman
%A Yang, Yiming
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%A Mausam
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F aggarwal-etal-2023-lets
%X A popular approach for improving the correctness of output from large language models (LLMs) is Self-Consistency - poll the LLM multiple times and output the most frequent solution. Existing Self-Consistency techniques always generate a constant number of samples per question, where a better approach will be to non-uniformly distribute the available budget based on the amount of agreement in the samples generated so far. In response, we introduce Adaptive-Consistency, a cost-efficient, model-agnostic technique that dynamically adjusts the number of samples per question using a lightweight stopping criterion. Our experiments over 17 reasoning and code generation datasets and three LLMs demonstrate that Adaptive-Consistency reduces sample budget by up to 7.9 times with an average accuracy drop of less than 0.1%
%R 10.18653/v1/2023.emnlp-main.761
%U https://aclanthology.org/2023.emnlp-main.761
%U https://doi.org/10.18653/v1/2023.emnlp-main.761
%P 12375-12396

Markdown (Informal)

[Let’s Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs](https://aclanthology.org/2023.emnlp-main.761) (Aggarwal et al., EMNLP 2023)

• Let’s Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs (Aggarwal et al., EMNLP 2023)

ACL

• Pranjal Aggarwal, Aman Madaan, Yiming Yang, and Mausam. 2023. Let’s Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 12375–12396, Singapore. Association for Computational Linguistics.