On the role of dialogue models in the age of large language models.

Wells, Simon; Snaith, Mark

Abstract

We argue that Machine learning, in particular the currently prevalent generation of Large Language Models (LLMs), can work constructively with existing normative models of dialogue as exemplified by dialogue games, specifically their computational applications within, for example, inter-agent communication and automated dialogue management. Furthermore we argue that this relationship is bi-directional, that some uses of dialogue games benefit from increased functionality due to the specific capabilities of LLMs, whilst LLMs benefit from externalised models of, variously, problematic, normative, or idealised behaviour. Machine Learning (ML) approaches, especially LLMs , appear to be making great advances against long-standing Artificial Intelligence challenges. In particular, LLMs are increasingly achieving successes in areas both adjacent to, and overlapping with, those of interest to the Computational Models of Natural Argument community. A prevalent opinion, not without some basis, within the ML research community is that many, if not all, AI challenges, will eventually be solved by ML models of increasing power and utility, negating the need for alternative or traditional approaches. An exemplar of this position, is the study of distinct models of dialogue for inter-agent communication when LLM based chatbots are increasingly able to surpass their performance in specific contexts. The trajectory of increased LLM capabilities suggests no reason that this trend will not continue, at least for some time. However, it is not the case that only the one, or the other approach, is necessary. Despite a tendency for LLMs to feature creep, and to appear to subsume additional areas of study, there are very good reasons to consider three modes of study of dialogue. Firstly, LLMs as their own individual field within ML, secondly, dialogue both in terms of actual human behaviour, which can exhibit wide quality standards, but also in terms of normative and idealised models, and thirdly, the fertile area in which the two overlap and can operate collaboratively. It is this third aspect with which this paper is concerned, for the first will occur anyway as researchers seek to map out the boundaries of what LLMs, as AI models, can actually achieve, and the second will continue, because the study of how people interact naturally through argument and dialogue will remain both fascinating and of objective value regardless of advances made in LLMs. However, where LLMs, Dialogue Models, and, for completion, people, come together, there is fertile ground for the development of principled models of interaction that are well-founded, well-regulated, and supportive of mixed-initiative interactions between humans and intelligent software agents.

Citation

WELLS, S. and SNAITH, M. 2023. On the role of dialogue models in the age of large language models. In Grasso, F., Green, N.L., Schneider, J. and Wells, S. (eds.) Proceedings of the 23rd Workshop on computational models of natural argument (CMNA 2023), 3 December 2023, [virtual event]. CEUR workshop proceedings, 3614. Aachen: CEUR-WS [online], pages 49-51. Available from: https://ceur-ws.org/Vol-3614/abstract2.pdf

• Conference Name: 23rd Workshop on computational models of natural argument (CMNA 2023)
• Conference Location: [virtual event]
• Start Date: Dec 3, 2023
• Acceptance Date: Oct 13, 2023
• Online Publication Date: Jan 9, 2024
• Publication Date: Dec 31, 2023
• Deposit Date: Feb 13, 2024
• Publicly Available Date: Feb 13, 2024
• Publisher: CEUR Workshop Proceedings
• Pages: 49-51
• Series Title: CEUR workshop proceedings
• Series Number: 3614
• Series ISSN: 1613-0073
• Keywords: Machine learning; Dialogue games; Computational applications; Dialogue models
• Public URL: https://rgu-repository.worktribe.com/output/2242873
• Publisher URL: https://ceur-ws.org/Vol-3614/abstract2.pdf