<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elaraby-etal-2026-improving">
    <titleInfo>
        <title>Improving Argument Saliency Coverage in Small LLMs for Long Legal Opinion Summarization via Sequence-Level Distillation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mohamed</namePart>
        <namePart type="family">Elaraby</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ahmed</namePart>
        <namePart type="family">Elhady</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Diane</namePart>
        <namePart type="family">Litman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>We show that sequence-level distillation from a capable long-context teacher model is a simple, annotation-free, and data-efficient strategy for improving argument saliency coverage in long legal opinion summarization, where small LLMs often struggle to retain the most salient argumentative content. Across student model sizes, distillation consistently surpasses tuning on expert-written summaries. We further demonstrate that most gains are achieved with as few as   10 training summaries, highlighting the strong data efficiency of teacher-generated supervision. Finally, we find that summary distillation is sufficient for improvements: reasoning-chain distillation remains competitive with summary-only distillation, but provides marginal benefit when combined with summary supervision.</abstract>
    <identifier type="citekey">elaraby-etal-2026-improving</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1825/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>41581</start>
            <end>41595</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Improving Argument Saliency Coverage in Small LLMs for Long Legal Opinion Summarization via Sequence-Level Distillation
%A Elaraby, Mohamed
%A Elhady, Ahmed
%A Litman, Diane
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F elaraby-etal-2026-improving
%X We show that sequence-level distillation from a capable long-context teacher model is a simple, annotation-free, and data-efficient strategy for improving argument saliency coverage in long legal opinion summarization, where small LLMs often struggle to retain the most salient argumentative content. Across student model sizes, distillation consistently surpasses tuning on expert-written summaries. We further demonstrate that most gains are achieved with as few as   10 training summaries, highlighting the strong data efficiency of teacher-generated supervision. Finally, we find that summary distillation is sufficient for improvements: reasoning-chain distillation remains competitive with summary-only distillation, but provides marginal benefit when combined with summary supervision.
%U https://aclanthology.org/2026.emnlp-main.1825/
%P 41581-41595

Markdown (Informal)

[Improving Argument Saliency Coverage in Small LLMs for Long Legal Opinion Summarization via Sequence-Level Distillation](https://aclanthology.org/2026.emnlp-main.1825/) (Elaraby et al., EMNLP 2026)

• Improving Argument Saliency Coverage in Small LLMs for Long Legal Opinion Summarization via Sequence-Level Distillation (Elaraby et al., EMNLP 2026)

ACL

• Mohamed Elaraby, Ahmed Elhady, and Diane Litman. 2026. Improving Argument Saliency Coverage in Small LLMs for Long Legal Opinion Summarization via Sequence-Level Distillation. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 41581–41595, Budapest, Hungary. Association for Computational Linguistics.