Enhancing Conflict Resolution in Language Models via Abstract Argumentation

TL;DR

This paper enhances language models' ability to resolve conflicts in dialogue by integrating abstract argumentation frameworks and explanations, leading to better generalization and transparency.

Contribution

It introduces a dataset and training method combining formal argumentation with LLMs, improving conflict resolution and interpretability in dialogue systems.

Findings

Models trained with explanations outperform those trained without.

Self-explanation capabilities improve transparency and conflict resolution.

Chain-of-thought approaches are less effective for conflict resolution.

Abstract

In recent years, large language models (LLMs) have made significant advancements in developing human-like and engaging dialogue systems. However, in tasks such as consensus-building and persuasion, LLMs often struggle to resolve conflicts arising from incomplete or inconsistent information, revealing their limitations in real-world applications. Given these limitations, abstract argumentation, a specialized logical framework designed to resolve conflicts and inconsistencies, becomes particularly relevant. In this paper, we aim to enhance the conflict-solving capabilities of LLMs by leveraging formal abstract argumentation, integrating language model learning with symbolic computation. To achieve this, we develop and curate a dataset comprising diverse abstract argumentation frameworks, accompanied by detailed explanations of the argument acceptability computation process. Subsequently, we fine-tune LLMs on this dataset, focusing on abstract conflict resolution tasks. As a comparative baseline, LLMs are also evaluated using a chain-of-thought approach, however, they fail to solve the conflict-based arguments effectively. Our experiments demonstrate that process explanations play a crucial role in learning. Models trained with explanations exhibit superior generalization accuracy compared to those trained solely on question-answer pairs. Furthermore, leveraging LLMs' self-explanation capabilities, our approach provides detailed illustrations that mitigate the lack of transparency typically associated with neural networks.