<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hengle-etal-2024-intent">
    <titleInfo>
        <title>Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Amey</namePart>
        <namePart type="family">Hengle</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aswini</namePart>
        <namePart type="family">Padhi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sahajpreet</namePart>
        <namePart type="family">Singh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anil</namePart>
        <namePart type="family">Bandhakavi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Md</namePart>
        <namePart type="given">Shad</namePart>
        <namePart type="family">Akhtar</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>2024-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kevin</namePart>
            <namePart type="family">Duh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Helena</namePart>
            <namePart type="family">Gomez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Steven</namePart>
            <namePart type="family">Bethard</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Mexico City, Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Counterspeech, defined as a response to mitigate online hate speech, is increasingly used as a non-censorial solution. The effectiveness of addressing hate speech involves dispelling the stereotypes, prejudices, and biases often subtly implied in brief, single-sentence statements or abuses. These expressions challenge language models, especially in seq2seq tasks, as model performance typically excels with longer contexts. Our study introduces CoARL, a novel framework enhancing counterspeech generation by modeling the pragmatic implications underlying social biases in hateful statements. The first two phases of CoARL involve sequential multi-instruction tuning, teaching the model to understand intents, reactions, and harms of offensive statements, and then learning task-specific low-rank adapter weights for generating intent-conditioned counterspeech. The final phase uses reinforcement learning to fine-tune outputs for effectiveness and nontoxicity. CoARL outperforms existing benchmarks in intent-conditioned counterspeech generation, showing an average improvement of ∼3 points in intent-conformity and ∼4 points in argument-quality metrics. Extensive human evaluation supports CoARL’s efficacy in generating superior and more context-appropriate responses compared to existing systems, including prominent LLMs like ChatGPT.</abstract>
    <identifier type="citekey">hengle-etal-2024-intent</identifier>
    <location>
        <url>https://aclanthology.org/2024.naacl-long.374</url>
    </location>
    <part>
        <date>2024-06</date>
        <extent unit="page">
            <start>6716</start>
            <end>6733</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF
%A Hengle, Amey
%A Padhi, Aswini
%A Singh, Sahajpreet
%A Bandhakavi, Anil
%A Akhtar, Md Shad
%A Chakraborty, Tanmoy
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F hengle-etal-2024-intent
%X Counterspeech, defined as a response to mitigate online hate speech, is increasingly used as a non-censorial solution. The effectiveness of addressing hate speech involves dispelling the stereotypes, prejudices, and biases often subtly implied in brief, single-sentence statements or abuses. These expressions challenge language models, especially in seq2seq tasks, as model performance typically excels with longer contexts. Our study introduces CoARL, a novel framework enhancing counterspeech generation by modeling the pragmatic implications underlying social biases in hateful statements. The first two phases of CoARL involve sequential multi-instruction tuning, teaching the model to understand intents, reactions, and harms of offensive statements, and then learning task-specific low-rank adapter weights for generating intent-conditioned counterspeech. The final phase uses reinforcement learning to fine-tune outputs for effectiveness and nontoxicity. CoARL outperforms existing benchmarks in intent-conditioned counterspeech generation, showing an average improvement of ∼3 points in intent-conformity and ∼4 points in argument-quality metrics. Extensive human evaluation supports CoARL’s efficacy in generating superior and more context-appropriate responses compared to existing systems, including prominent LLMs like ChatGPT.
%U https://aclanthology.org/2024.naacl-long.374
%P 6716-6733

Markdown (Informal)

[Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF](https://aclanthology.org/2024.naacl-long.374) (Hengle et al., NAACL 2024)

• Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF (Hengle et al., NAACL 2024)

ACL

• Amey Hengle, Aswini Padhi, Sahajpreet Singh, Anil Bandhakavi, Md Shad Akhtar, and Tanmoy Chakraborty. 2024. Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 6716–6733, Mexico City, Mexico. Association for Computational Linguistics.