<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2025-team">
    <titleInfo>
        <title>Team XSZ at BioLaySumm2025: Section-Wise Summarization, Retrieval-Augmented LLM, and Reinforcement Learning Fine-Tuning for Lay Summaries</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pengcheng</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sicheng</namePart>
        <namePart type="family">Shen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jieli</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hongyi</namePart>
        <namePart type="family">Xin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 24th Workshop on Biomedical Language Processing (Shared Tasks)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Sarvesh</namePart>
            <namePart type="family">Soni</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Dina</namePart>
            <namePart type="family">Demner-Fushman</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-276-3</identifier>
    </relatedItem>
    <abstract>We propose a unified, multi-stage lay summarization pipeline for BioLaySumm 2025 (Subtask 1.1) that (1) selects and summarizes key article sections via BioBART, (2) retrieves K-shot demonstrations using BGE embeddings for in-context Llama 3 8B prompting, (3) applies LoRA adapters to Llama 3 8B for supervised fine-tuning, (4) merges section summaries with a second BioBART pass, and (5) refines outputs through reinforcement learning (PPO &amp; GRPO) using a composite reward of factuality (AlignScore, SummaC), relevance (ROUGE-L, BERTScore), and readability (LENS, FKGL, DCRS, CLI). On PLOS and eLife validation sets, our complete systemreduces DCRS from 9.23 to 8.56 and reduces CLI from 12.98 to 12.65, ranking 3rd in readability. and outperforms llama3 finetune baseline in AlignScore 0.722 to 0.862, ranking 5th in factuality, demonstrating balanced gains across readability, relevance, and factuality.</abstract>
    <identifier type="citekey">xu-etal-2025-team</identifier>
    <identifier type="doi">10.18653/v1/2025.bionlp-share.33</identifier>
    <location>
        <url>https://aclanthology.org/2025.bionlp-share.33/</url>
    </location>
    <part>
        <date>2025-08</date>
        <extent unit="page">
            <start>275</start>
            <end>280</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Team XSZ at BioLaySumm2025: Section-Wise Summarization, Retrieval-Augmented LLM, and Reinforcement Learning Fine-Tuning for Lay Summaries
%A Xu, Pengcheng
%A Shen, Sicheng
%A Zhou, Jieli
%A Xin, Hongyi
%Y Soni, Sarvesh
%Y Demner-Fushman, Dina
%S Proceedings of the 24th Workshop on Biomedical Language Processing (Shared Tasks)
%D 2025
%8 August
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-276-3
%F xu-etal-2025-team
%X We propose a unified, multi-stage lay summarization pipeline for BioLaySumm 2025 (Subtask 1.1) that (1) selects and summarizes key article sections via BioBART, (2) retrieves K-shot demonstrations using BGE embeddings for in-context Llama 3 8B prompting, (3) applies LoRA adapters to Llama 3 8B for supervised fine-tuning, (4) merges section summaries with a second BioBART pass, and (5) refines outputs through reinforcement learning (PPO & GRPO) using a composite reward of factuality (AlignScore, SummaC), relevance (ROUGE-L, BERTScore), and readability (LENS, FKGL, DCRS, CLI). On PLOS and eLife validation sets, our complete systemreduces DCRS from 9.23 to 8.56 and reduces CLI from 12.98 to 12.65, ranking 3rd in readability. and outperforms llama3 finetune baseline in AlignScore 0.722 to 0.862, ranking 5th in factuality, demonstrating balanced gains across readability, relevance, and factuality.
%R 10.18653/v1/2025.bionlp-share.33
%U https://aclanthology.org/2025.bionlp-share.33/
%U https://doi.org/10.18653/v1/2025.bionlp-share.33
%P 275-280

Markdown (Informal)

[Team XSZ at BioLaySumm2025: Section-Wise Summarization, Retrieval-Augmented LLM, and Reinforcement Learning Fine-Tuning for Lay Summaries](https://aclanthology.org/2025.bionlp-share.33/) (Xu et al., BioNLP 2025)

• Team XSZ at BioLaySumm2025: Section-Wise Summarization, Retrieval-Augmented LLM, and Reinforcement Learning Fine-Tuning for Lay Summaries (Xu et al., BioNLP 2025)

ACL

• Pengcheng Xu, Sicheng Shen, Jieli Zhou, and Hongyi Xin. 2025. Team XSZ at BioLaySumm2025: Section-Wise Summarization, Retrieval-Augmented LLM, and Reinforcement Learning Fine-Tuning for Lay Summaries. In Proceedings of the 24th Workshop on Biomedical Language Processing (Shared Tasks), pages 275–280, Vienna, Austria. Association for Computational Linguistics.