Assistive Large Language Model Agents for Socially-Aware Negotiation Dialogues

Yuncheng Hua, Lizhen Qu, Reza Haf


Abstract
We develop assistive agents based on Large Language Models (LLMs) that aid interlocutors in business negotiations.Specifically, we simulate business negotiations by letting two LLM-based agents engage in role play. A third LLM acts as a remediator agent to rewrite utterances violating norms for improving negotiation outcomes.We introduce a simple tuning-free and label-free In-Context Learning (ICL) method to identify high-quality ICL exemplars for the remediator, where we propose a novel select criteria, called value impact, to measure the quality of the negotiation outcomes. We provide rich empirical evidence to demonstrate its effectiveness in negotiations across three different negotiation topics. We have released our source code and the generated dataset at: https://github.com/tk1363704/SADAS.
Anthology ID:
2024.findings-emnlp.473
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8047–8074
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.473
DOI:
Bibkey:
Cite (ACL):
Yuncheng Hua, Lizhen Qu, and Reza Haf. 2024. Assistive Large Language Model Agents for Socially-Aware Negotiation Dialogues. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 8047–8074, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Assistive Large Language Model Agents for Socially-Aware Negotiation Dialogues (Hua et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.473.pdf