Formal Dialogue and Large Language Models

Snaith, Mark; Wells, Simon

Abstract

In this paper, we present preliminary work into combining formal models of dialogue and large language models, before going on to discuss how this provides a foundation for similar approaches involving computational models of argument. First, we address the twin issues of how a formal dialogue game can usefully regulate dialogical utterances generated by an LLM during an extended, goal-oriented conversation, and conversely, how LLMs can close the human-level language generation gap associated with formal dialogue games. We then proceed to identify how our solution to these issues can underpin future work towards using computational argumentation to provide reasoning-like capabilities to LLMs, and using LLMs for tasks such as searching and summarisation of analysed argument data.

Citation

Snaith, M., & Wells, S. (2024, October). Formal Dialogue and Large Language Models. Presented at SICSA Workshop on Reasoning, Evaluation and Application of Large Language Models (SICSA-REALLM 2024), Aberdeen, UK

• Presentation Conference Type: Conference Paper (published)
• Conference Name: SICSA Workshop on Reasoning, Evaluation and Application of Large Language Models (SICSA-REALLM 2024)
• Start Date: Oct 17, 2024
• Acceptance Date: Oct 1, 2024
• Online Publication Date: Nov 4, 2024
• Publication Date: 2024
• Deposit Date: Feb 12, 2025
• Publicly Available Date: Feb 13, 2025
• Print ISSN: 1613-0073
• Publisher: CEUR Workshop Proceedings
• Peer Reviewed: Peer Reviewed
• Volume: 3822
• Pages: 24-31
• Series ISSN: 1613-0073
• Book Title: Proceedings of the SICSA Workshop on Reasoning, Evaluation and Application of Large Language Models (SICSA-REALLM 2024)
• Keywords: Formal dialogue, argumentation
• Public URL: http://researchrepository.napier.ac.uk/Output/4117882
• Publisher URL: https://ceur-ws.org/Vol-3822/