<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pitre-etal-2026-refeedgraph">
    <titleInfo>
        <title>ReFeedGraph: Graph-Grounded Reusable Feedback for Debate Improvement</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Priya</namePart>
        <namePart type="family">Pitre</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Omkar</namePart>
        <namePart type="given">J</namePart>
        <namePart type="family">Joshi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Timon</namePart>
        <namePart type="family">Ziegenbein</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Henning</namePart>
        <namePart type="family">Wachsmuth</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>Debate feedback is useful only when it explains why a side lost and how that side can revise to become more competitive. However, LLM-generated feedback often sounds polished while remaining generic and vague. We introduce ReFeedGraph, a graph-based method that turns prior debate feedback into reusable principles. It collects multi-framework judge feedback, extracts weaknesses and actionable suggestions, abstracts them into principles, and stores them in a graph. For a new debate, ReFeedGraph retrieves relevant principles and adapts them into targeted revision feedback. We evaluate the generated feedback by recording whether it improves the weaker side after rewriting. Across three existing datasets (DebateArt, Intelligence Squared, and British Parliamentary debates), ReFeedGraph outperforms direct LLM and structured-prompt baselines, producing more specific and actionable feedback that leads to winning more debates.</abstract>
    <identifier type="citekey">pitre-etal-2026-refeedgraph</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.678/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>15621</start>
            <end>15640</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ReFeedGraph: Graph-Grounded Reusable Feedback for Debate Improvement
%A Pitre, Priya
%A Joshi, Omkar J.
%A Ziegenbein, Timon
%A Wachsmuth, Henning
%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 pitre-etal-2026-refeedgraph
%X Debate feedback is useful only when it explains why a side lost and how that side can revise to become more competitive. However, LLM-generated feedback often sounds polished while remaining generic and vague. We introduce ReFeedGraph, a graph-based method that turns prior debate feedback into reusable principles. It collects multi-framework judge feedback, extracts weaknesses and actionable suggestions, abstracts them into principles, and stores them in a graph. For a new debate, ReFeedGraph retrieves relevant principles and adapts them into targeted revision feedback. We evaluate the generated feedback by recording whether it improves the weaker side after rewriting. Across three existing datasets (DebateArt, Intelligence Squared, and British Parliamentary debates), ReFeedGraph outperforms direct LLM and structured-prompt baselines, producing more specific and actionable feedback that leads to winning more debates.
%U https://aclanthology.org/2026.emnlp-main.678/
%P 15621-15640

Markdown (Informal)

[ReFeedGraph: Graph-Grounded Reusable Feedback for Debate Improvement](https://aclanthology.org/2026.emnlp-main.678/) (Pitre et al., EMNLP 2026)

• ReFeedGraph: Graph-Grounded Reusable Feedback for Debate Improvement (Pitre et al., EMNLP 2026)

ACL

• Priya Pitre, Omkar J. Joshi, Timon Ziegenbein, and Henning Wachsmuth. 2026. ReFeedGraph: Graph-Grounded Reusable Feedback for Debate Improvement. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 15621–15640, Budapest, Hungary. Association for Computational Linguistics.