<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nath-etal-2026-counter">
    <titleInfo>
        <title>Counter with Evidence! A Multi-Agent Memory Efficient Reasoning Framework for Hate Category Informed Counterspeech Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sujoy</namePart>
        <namePart type="family">Nath</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aswini</namePart>
        <namePart type="family">Kumar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tanmoy</namePart>
        <namePart type="family">Chakraborty</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>Counterspeech effectively neutralizes the impact of online hate. Although prior work explores automated counterspeech generation, it largely emphasizes stylistic control while treating hate speech as homogeneous, overlooking that distinct forms of abuse require fundamentally different counterspeech strategies. To address this gap, we introduce FIRE (Factuality Informed Multi-Agent Reasoning Framework) that first decomposes hate speech into one of the five distinct categories (misinformation, stereotype, conspiracy, dehumanizing, non-factual), and then maps it to a targeted counterspeech style. To facilitate FIRE, we curate FactualCS, a novel dataset of 4,784 instances that provides the annotations regarding hate categories, reasoning traces, and evidence mappings, which are critical elements for grounded generation that are missing in prior work. A comprehensive evaluation across 28 baseline configurations demonstrates that FIRE significantly surpasses existing methods, despite using compact agents (&lt;2B). FIRE achieves a \sim 12% and \sim 11% improvements in factual and category-specific accuracy respectively, while simultaneously reducing toxicity by \sim 11% relative to the strongest baselines. Further human evaluation confirms that responses generated by FIRE are significantly preferred over the strongest baselines, underscoring its effectiveness for real-world deployment. These findings show that decomposing the underlying intent of hate speech is essential for generating safe, effective, and contextually precise counterspeech.</abstract>
    <identifier type="citekey">nath-etal-2026-counter</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1647/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>37435</start>
            <end>37458</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Counter with Evidence! A Multi-Agent Memory Efficient Reasoning Framework for Hate Category Informed Counterspeech Generation
%A Nath, Sujoy
%A Kumar, Aswini
%A Chakraborty, Tanmoy
%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 nath-etal-2026-counter
%X Counterspeech effectively neutralizes the impact of online hate. Although prior work explores automated counterspeech generation, it largely emphasizes stylistic control while treating hate speech as homogeneous, overlooking that distinct forms of abuse require fundamentally different counterspeech strategies. To address this gap, we introduce FIRE (Factuality Informed Multi-Agent Reasoning Framework) that first decomposes hate speech into one of the five distinct categories (misinformation, stereotype, conspiracy, dehumanizing, non-factual), and then maps it to a targeted counterspeech style. To facilitate FIRE, we curate FactualCS, a novel dataset of 4,784 instances that provides the annotations regarding hate categories, reasoning traces, and evidence mappings, which are critical elements for grounded generation that are missing in prior work. A comprehensive evaluation across 28 baseline configurations demonstrates that FIRE significantly surpasses existing methods, despite using compact agents (<2B). FIRE achieves a \sim 12% and \sim 11% improvements in factual and category-specific accuracy respectively, while simultaneously reducing toxicity by \sim 11% relative to the strongest baselines. Further human evaluation confirms that responses generated by FIRE are significantly preferred over the strongest baselines, underscoring its effectiveness for real-world deployment. These findings show that decomposing the underlying intent of hate speech is essential for generating safe, effective, and contextually precise counterspeech.
%U https://aclanthology.org/2026.emnlp-main.1647/
%P 37435-37458

Markdown (Informal)

[Counter with Evidence! A Multi-Agent Memory Efficient Reasoning Framework for Hate Category Informed Counterspeech Generation](https://aclanthology.org/2026.emnlp-main.1647/) (Nath et al., EMNLP 2026)

• Counter with Evidence! A Multi-Agent Memory Efficient Reasoning Framework for Hate Category Informed Counterspeech Generation (Nath et al., EMNLP 2026)

ACL

• Sujoy Nath, Aswini Kumar, and Tanmoy Chakraborty. 2026. Counter with Evidence! A Multi-Agent Memory Efficient Reasoning Framework for Hate Category Informed Counterspeech Generation. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 37435–37458, Budapest, Hungary. Association for Computational Linguistics.