<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jha-etal-2026-diplomat">
    <titleInfo>
        <title>DIPLOMAT: Dialogue-Span-Aware Direct Preference Optimization for Polite Persuasive Workplace Negotiation Dialogues</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bibhuti</namePart>
        <namePart type="family">Jha</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rishikant</namePart>
        <namePart type="family">Chigrupaatii</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Priyanshu</namePart>
        <namePart type="family">Priya</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Asif</namePart>
        <namePart type="family">Ekbal</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>Effective workplace negotiation requires balancing multiple objectives, including achieving task goals, preserving professional relationships, and resolving conflicts constructively. However, misunderstandings, misaligned preferences, and interpersonal friction often impede successful outcomes. Politeness mitigates these challenges by fostering trust, reducing tension, and preventing escalation, and persuasive communication helps overcome resistance, align preferences, and guide participants toward mutually beneficial agreements. Motivated by these insights, we present **DIPLOMAT**, a dialogue system for polite and persuasive workplace negotiation. To support its development, we introduce **PROWESS**, a dataset of multi-turn workplace negotiation dialogues generated via a multi-agent framework and enriched with negotiation strategies, politeness levels, and persuasive strategies. **DIPLOMAT** is trained using Dialogue-Span-Aware Direct Preference Optimization (DSA-DPO), a novel preference learning objective that identifies key dialogue spans for preference alignment. This enables **DIPLOMAT** to generate contextually coherent responses that employ intended negotiation strategies, maintain politeness, and incorporate effective persuasion strategies throughout interactions. Automatic and human evaluations on **PROWESS** confirm that **DIPLOMAT** consistently outperforms baselines in generating coherent, polite, and persuasive negotiation responses.</abstract>
    <identifier type="citekey">jha-etal-2026-diplomat</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2627/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>59709</start>
            <end>59749</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DIPLOMAT: Dialogue-Span-Aware Direct Preference Optimization for Polite Persuasive Workplace Negotiation Dialogues
%A Jha, Bibhuti
%A Chigrupaatii, Rishikant
%A Priya, Priyanshu
%A Ekbal, Asif
%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 jha-etal-2026-diplomat
%X Effective workplace negotiation requires balancing multiple objectives, including achieving task goals, preserving professional relationships, and resolving conflicts constructively. However, misunderstandings, misaligned preferences, and interpersonal friction often impede successful outcomes. Politeness mitigates these challenges by fostering trust, reducing tension, and preventing escalation, and persuasive communication helps overcome resistance, align preferences, and guide participants toward mutually beneficial agreements. Motivated by these insights, we present **DIPLOMAT**, a dialogue system for polite and persuasive workplace negotiation. To support its development, we introduce **PROWESS**, a dataset of multi-turn workplace negotiation dialogues generated via a multi-agent framework and enriched with negotiation strategies, politeness levels, and persuasive strategies. **DIPLOMAT** is trained using Dialogue-Span-Aware Direct Preference Optimization (DSA-DPO), a novel preference learning objective that identifies key dialogue spans for preference alignment. This enables **DIPLOMAT** to generate contextually coherent responses that employ intended negotiation strategies, maintain politeness, and incorporate effective persuasion strategies throughout interactions. Automatic and human evaluations on **PROWESS** confirm that **DIPLOMAT** consistently outperforms baselines in generating coherent, polite, and persuasive negotiation responses.
%U https://aclanthology.org/2026.emnlp-main.2627/
%P 59709-59749

Markdown (Informal)

[DIPLOMAT: Dialogue-Span-Aware Direct Preference Optimization for Polite Persuasive Workplace Negotiation Dialogues](https://aclanthology.org/2026.emnlp-main.2627/) (Jha et al., EMNLP 2026)

• DIPLOMAT: Dialogue-Span-Aware Direct Preference Optimization for Polite Persuasive Workplace Negotiation Dialogues (Jha et al., EMNLP 2026)

ACL

• Bibhuti Jha, Rishikant Chigrupaatii, Priyanshu Priya, and Asif Ekbal. 2026. DIPLOMAT: Dialogue-Span-Aware Direct Preference Optimization for Polite Persuasive Workplace Negotiation Dialogues. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 59709–59749, Budapest, Hungary. Association for Computational Linguistics.