<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rajaee-etal-2026-best">
    <titleInfo>
        <title>Best-of-L: Cross-Lingual Reward Modeling for Mathematical Reasoning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sara</namePart>
        <namePart type="family">Rajaee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rochelle</namePart>
        <namePart type="family">Choenni</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ekaterina</namePart>
        <namePart type="family">Shutova</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Christof</namePart>
        <namePart type="family">Monz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Vera</namePart>
            <namePart type="family">Demberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kentaro</namePart>
            <namePart type="family">Inui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Marquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-386-9</identifier>
    </relatedItem>
    <abstract>While the reasoning abilities of large language models (LLMs) continue to advance, it remains underexplored how such abilities vary across languages in multilingual LLMs and whether different languages generate distinct reasoning paths. In this work, we show that reasoning traces generated in different languages often provide complementary signals for mathematical reasoning. We propose cross-lingual outcome reward modeling, a framework that ranks candidate reasoning traces across languages rather than within a single language.Our experiments on the MGSM benchmark show that cross-lingual reward modeling improves accuracy by up to 10 points compared to using reward modeling within a single language, benefiting both high- and low-resource languages.Notably, cross-lingual sampling improves English performance under low inference budgets, despite English being the strongest individual language.Our findings reveal new opportunities to improve multilingual reasoning by leveraging the complementary strengths of diverse languages.</abstract>
    <identifier type="citekey">rajaee-etal-2026-best</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-eacl.99/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>1930</start>
            <end>1939</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Best-of-L: Cross-Lingual Reward Modeling for Mathematical Reasoning
%A Rajaee, Sara
%A Choenni, Rochelle
%A Shutova, Ekaterina
%A Monz, Christof
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F rajaee-etal-2026-best
%X While the reasoning abilities of large language models (LLMs) continue to advance, it remains underexplored how such abilities vary across languages in multilingual LLMs and whether different languages generate distinct reasoning paths. In this work, we show that reasoning traces generated in different languages often provide complementary signals for mathematical reasoning. We propose cross-lingual outcome reward modeling, a framework that ranks candidate reasoning traces across languages rather than within a single language.Our experiments on the MGSM benchmark show that cross-lingual reward modeling improves accuracy by up to 10 points compared to using reward modeling within a single language, benefiting both high- and low-resource languages.Notably, cross-lingual sampling improves English performance under low inference budgets, despite English being the strongest individual language.Our findings reveal new opportunities to improve multilingual reasoning by leveraging the complementary strengths of diverse languages.
%U https://aclanthology.org/2026.findings-eacl.99/
%P 1930-1939

Markdown (Informal)

[Best-of-L: Cross-Lingual Reward Modeling for Mathematical Reasoning](https://aclanthology.org/2026.findings-eacl.99/) (Rajaee et al., Findings 2026)

• Best-of-L: Cross-Lingual Reward Modeling for Mathematical Reasoning (Rajaee et al., Findings 2026)

ACL

• Sara Rajaee, Rochelle Choenni, Ekaterina Shutova, and Christof Monz. 2026. Best-of-L: Cross-Lingual Reward Modeling for Mathematical Reasoning. In Findings of the Association for Computational Linguistics: EACL 2026, pages 1930–1939, Rabat, Morocco. Association for Computational Linguistics.