<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="seo-etal-2024-rethinking">
    <titleInfo>
        <title>Rethinking Code Refinement: Learning to Judge Code Efficiency</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Minju</namePart>
        <namePart type="family">Seo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jinheon</namePart>
        <namePart type="family">Baek</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sung</namePart>
        <namePart type="given">Ju</namePart>
        <namePart type="family">Hwang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Large Language Models (LLMs) have demonstrated impressive capabilities in understanding and generating codes. Due to these capabilities, many recent methods are proposed to automatically refine the codes with LLMs. However, we should rethink that the refined codes (from LLMs and even humans) are not always more efficient than their original versions. On the other hand, running two different versions of codes and comparing them every time is not ideal and time-consuming. Therefore, in this work, we propose a novel method based on the code language model that is trained to judge the efficiency between two different codes (generated across humans and machines) by either classifying the superior one or predicting the relative improvement. We validate our method on multiple programming languages with multiple refinement steps, demonstrating that the proposed method can effectively distinguish between more and less efficient versions of code.</abstract>
    <identifier type="citekey">seo-etal-2024-rethinking</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-emnlp.645</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>11045</start>
            <end>11056</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Rethinking Code Refinement: Learning to Judge Code Efficiency
%A Seo, Minju
%A Baek, Jinheon
%A Hwang, Sung Ju
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F seo-etal-2024-rethinking
%X Large Language Models (LLMs) have demonstrated impressive capabilities in understanding and generating codes. Due to these capabilities, many recent methods are proposed to automatically refine the codes with LLMs. However, we should rethink that the refined codes (from LLMs and even humans) are not always more efficient than their original versions. On the other hand, running two different versions of codes and comparing them every time is not ideal and time-consuming. Therefore, in this work, we propose a novel method based on the code language model that is trained to judge the efficiency between two different codes (generated across humans and machines) by either classifying the superior one or predicting the relative improvement. We validate our method on multiple programming languages with multiple refinement steps, demonstrating that the proposed method can effectively distinguish between more and less efficient versions of code.
%U https://aclanthology.org/2024.findings-emnlp.645
%P 11045-11056

Markdown (Informal)

[Rethinking Code Refinement: Learning to Judge Code Efficiency](https://aclanthology.org/2024.findings-emnlp.645) (Seo et al., Findings 2024)

• Rethinking Code Refinement: Learning to Judge Code Efficiency (Seo et al., Findings 2024)

ACL

• Minju Seo, Jinheon Baek, and Sung Ju Hwang. 2024. Rethinking Code Refinement: Learning to Judge Code Efficiency. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 11045–11056, Miami, Florida, USA. Association for Computational Linguistics.