<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="uluslu-etal-2025-robust">
    <titleInfo>
        <title>Robust Native Language Identification through Agentic Decomposition</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ahmet</namePart>
        <namePart type="given">Yavuz</namePart>
        <namePart type="family">Uluslu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tannon</namePart>
        <namePart type="family">Kew</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tilia</namePart>
        <namePart type="family">Ellendorff</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gerold</namePart>
        <namePart type="family">Schneider</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rico</namePart>
        <namePart type="family">Sennrich</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-332-6</identifier>
    </relatedItem>
    <abstract>Large language models (LLMs) often achieve high performance in native language identification (NLI) benchmarks by leveraging superficial contextual clues such as names, locations, and cultural stereotypes, rather than the underlying linguistic patterns indicative of native language (L1) influence. To improve robustness, previous work has instructed LLMs to disregard such clues. In this work, we demonstrate that such a strategy is unreliable and model predictions can be easily altered by misleading hints. To address this problem, we introduce an agentic NLI pipeline inspired by forensic linguistics, where specialized agents accumulate and categorize diverse linguistic evidence before an independent final overall assessment. In this final assessment, a goal-aware coordinating agent synthesizes all evidence to make the NLI prediction. On two benchmark datasets, our approach significantly enhances NLI robustness against misleading contextual clues and performance consistency compared to standard prompting methods.</abstract>
    <identifier type="citekey">uluslu-etal-2025-robust</identifier>
    <location>
        <url>https://aclanthology.org/2025.emnlp-main.423/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>8409</start>
            <end>8425</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Robust Native Language Identification through Agentic Decomposition
%A Uluslu, Ahmet Yavuz
%A Kew, Tannon
%A Ellendorff, Tilia
%A Schneider, Gerold
%A Sennrich, Rico
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F uluslu-etal-2025-robust
%X Large language models (LLMs) often achieve high performance in native language identification (NLI) benchmarks by leveraging superficial contextual clues such as names, locations, and cultural stereotypes, rather than the underlying linguistic patterns indicative of native language (L1) influence. To improve robustness, previous work has instructed LLMs to disregard such clues. In this work, we demonstrate that such a strategy is unreliable and model predictions can be easily altered by misleading hints. To address this problem, we introduce an agentic NLI pipeline inspired by forensic linguistics, where specialized agents accumulate and categorize diverse linguistic evidence before an independent final overall assessment. In this final assessment, a goal-aware coordinating agent synthesizes all evidence to make the NLI prediction. On two benchmark datasets, our approach significantly enhances NLI robustness against misleading contextual clues and performance consistency compared to standard prompting methods.
%U https://aclanthology.org/2025.emnlp-main.423/
%P 8409-8425

Markdown (Informal)

[Robust Native Language Identification through Agentic Decomposition](https://aclanthology.org/2025.emnlp-main.423/) (Uluslu et al., EMNLP 2025)

• Robust Native Language Identification through Agentic Decomposition (Uluslu et al., EMNLP 2025)

ACL

• Ahmet Yavuz Uluslu, Tannon Kew, Tilia Ellendorff, Gerold Schneider, and Rico Sennrich. 2025. Robust Native Language Identification through Agentic Decomposition. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 8409–8425, Suzhou, China. Association for Computational Linguistics.