Publication Type

Journal Article

Version

publishedVersion

Publication Date

2-2025

Abstract

Large language models (LLMs) such as GPT-4 have been creatively harnessed in the conflict resolution arena as dialogue agents interacting with humans within negotiations, due to their capacity for in-context learning and giving human-like responses. In light of the burgeoning use of LLMs in conflict resolution training, a pilot study was conducted to ascertain the desirability of using dialogue agents built on GPT-4 in conducting simulations for students learning negotiation skills. This article discusses insights gained from the study on the reliability of LLM agents in following prompts for negotiation simulations; notable negotiation behaviour of the LLM agent; the degree to which learning objectives are achieved; and how closely the LLM agent’s responses resemble human behaviour. It further offers reflections on appropriate ways to harness LLM agents in future conflict resolution training.

Keywords

large language model, generative AI, GPT-4, negotiation, conflict resolution

Discipline

Artificial Intelligence and Robotics | Dispute Resolution and Arbitration | Science and Technology Law

Research Areas

Dispute Resolution

Publication

Australasian Dispute Resolution Journal

Volume

33

Issue

3

First Page

157

Last Page

177

ISSN

1441-7847

Identifier

10.3316/informit.T2025060100008000475951305

Publisher

Thomson Reuters (Professional)

Additional URL

https://search.informit.org/doi/10.3316/informit.T2025060100008000475951305

Download

Share

COinS