Abstract
In this article, we introduce LLMediator, an experimental platform designed to enhance online dispute resolution (ODR) by utilizing capabilities of state-of-the-art large language models (LLMs) such as GPT-4. In the context of high-volume, low-intensity legal disputes, alternative dispute resolution methods such as negotiation and mediation offer accessible and cooperative solutions for laypeople. These approaches can be carried out online on ODR platforms. LLMediator aims to improve the efficacy of such processes by leveraging GPT-4 to reformulate user messages, draft mediator responses, and potentially autonomously engage in the discussions. We present and discuss several features of LLMediator and conduct initial qualitative evaluations, demonstrating the potential for LLMs to support ODR and facilitate amicable settlements. The initial proof of concept is promising and opens up avenues for further research in AI-assisted negotiation and mediation.
GPT-4 mediating:
- Reformulating inflammatory messages: detect this language, offer alternative formulation. User choose to send original, send reformulated, or edit.
- keyword search
- “You are an ODR platform. You are given the chat message of a party. Reformulate the message to maintain the content, but make it less confrontational and more encouraging for an amicable settlement. Respond directly with the reformulated message, do not explain.”
- Drafting messages for mediator: when negotiation is in deadlock, mediator can press a button in interface to generate a draft a suggested message that guides the parties toward friendly resolution.
- Autonomously intervening in negotiation: when “dispute value is too low for employing a human mediator”.
They haven’t tested this in a real setting.