DS@GT at Touché: Large Language Models for Retrieval-Augmented Debate
This is an incremental study on LLMs for structured debate and evaluation, relevant to researchers in conversational AI and debate systems.
The study tackled the problem of using large language models (LLMs) for retrieval-augmented debate, finding that while they perform well with related arguments, they tend to be verbose in responses yet consistent in evaluation.
Large Language Models (LLMs) demonstrate strong conversational abilities. In this Working Paper, we study them in the context of debating in two ways: their ability to perform in a structured debate along with a dataset of arguments to use and their ability to evaluate utterances throughout the debate. We deploy six leading publicly available models from three providers for the Retrieval-Augmented Debate and Evaluation. The evaluation is performed by measuring four key metrics: Quality, Quantity, Manner, and Relation. Throughout this task, we found that although LLMs perform well in debates when given related arguments, they tend to be verbose in responses yet consistent in evaluation. The accompanying source code for this paper is located at https://github.com/dsgt-arc/touche-2025-rad.