<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fujinuma-2026-contrastive">
    <titleInfo>
        <title>Contrastive Decoding Mitigates Score Range Bias in LLM-as-a-Judge</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yoshinari</namePart>
        <namePart type="family">Fujinuma</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>Large Language Models (LLMs) are commonly used as evaluators in various applications, but the reliability of the outcomes remains a challenge. One such challenge is using LLMs-as-judges for direct assessment, i.e., assigning scores from a specified range without any references. Using summarization as our primary testbed, we first show that this challenge stems from LLM judge outputs being associated with score range bias, i.e., LLM judge outputs are highly sensitive to pre-defined score ranges. We also show that similar biases exist among models from the same family. We then mitigate this bias through contrastive decoding, achieving up to 11.7% relative improvement in Spearman correlation with human judgments, averaged across score ranges.</abstract>
    <identifier type="citekey">fujinuma-2026-contrastive</identifier>
    <identifier type="doi">10.18653/v1/2026.findings-acl.657</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-acl.657/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>13404</start>
            <end>13418</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Contrastive Decoding Mitigates Score Range Bias in LLM-as-a-Judge
%A Fujinuma, Yoshinari
%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 fujinuma-2026-contrastive
%X Large Language Models (LLMs) are commonly used as evaluators in various applications, but the reliability of the outcomes remains a challenge. One such challenge is using LLMs-as-judges for direct assessment, i.e., assigning scores from a specified range without any references. Using summarization as our primary testbed, we first show that this challenge stems from LLM judge outputs being associated with score range bias, i.e., LLM judge outputs are highly sensitive to pre-defined score ranges. We also show that similar biases exist among models from the same family. We then mitigate this bias through contrastive decoding, achieving up to 11.7% relative improvement in Spearman correlation with human judgments, averaged across score ranges.
%R 10.18653/v1/2026.findings-acl.657
%U https://aclanthology.org/2026.findings-acl.657/
%U https://doi.org/10.18653/v1/2026.findings-acl.657
%P 13404-13418

Markdown (Informal)

[Contrastive Decoding Mitigates Score Range Bias in LLM-as-a-Judge](https://aclanthology.org/2026.findings-acl.657/) (Fujinuma, Findings 2026)

• Contrastive Decoding Mitigates Score Range Bias in LLM-as-a-Judge (Fujinuma, Findings 2026)

ACL

• Yoshinari Fujinuma. 2026. Contrastive Decoding Mitigates Score Range Bias in LLM-as-a-Judge. In Findings of the Association for Computational Linguistics: ACL 2026, pages 13404–13418, San Diego, California, United States. Association for Computational Linguistics.