Metraipolis › archive › dc_e11b88b3fb8a

DIPLOMAT: Dialogue-Span-Aware Direct Preference Optimization for Polite Persuasive Workplace Negotiation Dialogues — arXiv:2609.22256

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.22256
License (as archived)
CC0-1.0
Archived
2026-10-09T06:49:27.556Z
SHA-256 of the archived text
746352ff5f52c533330a07fa65d829b936028e857f2363edbc9f9b05bf837a57
Stable URL of this page
https://metraipolis.com/documento/dc_e11b88b3fb8a

How to cite

DIPLOMAT: Dialogue-Span-Aware Direct Preference Optimization for Polite Persuasive Workplace Negotiation Dialogues — arXiv:2609.22256 — arXiv (en), https://arxiv.org/abs/2609.22256 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e11b88b3fb8a (Metraipolis archive dc_e11b88b3fb8a, sha256 746352ff5f52c533330a07fa65d829b936028e857f2363edbc9f9b05bf837a57)
BibTeX
@misc{dce11b88b3fb8a,
  title = {DIPLOMAT: Dialogue-Span-Aware Direct Preference Optimization for Polite Persuasive Workplace Negotiation Dialogues — arXiv:2609.22256},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22256},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e11b88b3fb8a; sha256 746352ff5f52c533330a07fa65d829b936028e857f2363edbc9f9b05bf837a57},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22256. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 withnegotiation strategies, politeness levels, 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 evaluation on PROWESS confirm that DIPLOMAT consistently outperforms baselines in generating coherent, polite, and persuasive negotiation responses.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.22256 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T06:48:44.920Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).