<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lo-mitkov-2025-anaphora">
    <titleInfo>
        <title>Does Anaphora Resolution Improve LLM Fine-Tuning for Summarisation?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yi</namePart>
        <namePart type="given">Chun</namePart>
        <namePart type="family">Lo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ruslan</namePart>
        <namePart type="family">Mitkov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Alicia</namePart>
            <namePart type="family">Picazo-Izquierdo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ernesto</namePart>
            <namePart type="given">Luis</namePart>
            <namePart type="family">Estevanell-Valladares</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rafael</namePart>
            <namePart type="given">Muñoz</namePart>
            <namePart type="family">Guillena</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Raúl</namePart>
            <namePart type="given">García</namePart>
            <namePart type="family">Cerdá</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This study investigates whether adding anaphora resolution as a preprocessing step before fine-tuning the text summarisation application in LLM can improve the quality of summary output. Two sets of training with the T5-base model and BART-large model using the SAMSum dataset were conducted. One uses the original text and the other uses the text processed by a simplified version of MARS (Mitkov’s Anaphora Resolution System). The experiment reveals that when T5-base model is fine-tuned on the anaphora-resolved inputs, the ROUGE metrics are improved. In contrast, BART-large model only has a slight improvement after fine-tuning under the same conditions, which is not statistically significant. Further analysis of the generated summaries indicates that anaphora resolution is helpful in semantic alignment.</abstract>
    <identifier type="citekey">lo-mitkov-2025-anaphora</identifier>
    <location>
        <url>https://aclanthology.org/2025.r2lm-1.7/</url>
    </location>
    <part>
        <date>2025-09</date>
        <extent unit="page">
            <start>59</start>
            <end>66</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Does Anaphora Resolution Improve LLM Fine-Tuning for Summarisation?
%A Lo, Yi Chun
%A Mitkov, Ruslan
%Y Picazo-Izquierdo, Alicia
%Y Estevanell-Valladares, Ernesto Luis
%Y Mitkov, Ruslan
%Y Guillena, Rafael Muñoz
%Y Cerdá, Raúl García
%S Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F lo-mitkov-2025-anaphora
%X This study investigates whether adding anaphora resolution as a preprocessing step before fine-tuning the text summarisation application in LLM can improve the quality of summary output. Two sets of training with the T5-base model and BART-large model using the SAMSum dataset were conducted. One uses the original text and the other uses the text processed by a simplified version of MARS (Mitkov’s Anaphora Resolution System). The experiment reveals that when T5-base model is fine-tuned on the anaphora-resolved inputs, the ROUGE metrics are improved. In contrast, BART-large model only has a slight improvement after fine-tuning under the same conditions, which is not statistically significant. Further analysis of the generated summaries indicates that anaphora resolution is helpful in semantic alignment.
%U https://aclanthology.org/2025.r2lm-1.7/
%P 59-66

Markdown (Informal)

[Does Anaphora Resolution Improve LLM Fine-Tuning for Summarisation?](https://aclanthology.org/2025.r2lm-1.7/) (Lo & Mitkov, R2LM 2025)

• Does Anaphora Resolution Improve LLM Fine-Tuning for Summarisation? (Lo & Mitkov, R2LM 2025)

ACL

• Yi Chun Lo and Ruslan Mitkov. 2025. Does Anaphora Resolution Improve LLM Fine-Tuning for Summarisation?. In Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models, pages 59–66, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.