Enhancing Conflict Resolution in Language Models via Abstract Argumentation

2024-12-21

AI Summary

Large language models (LLMs) struggle to identify and resolve conflicts arising from incomplete or inconsistent information in consensus-building and persuasion tasks, resulting in poor interpretability and weak generalization. Method: This paper introduces the first systematic integration of abstract argumentation—a formal framework for reasoning about conflicting claims—into LLM training. We propose a fine-grained, process-explainable conflict resolution paradigm combining argument-structure modeling, self-explanatory generation, and process-aware supervised learning. Our curated argumentation framework dataset explicitly supports modeling premise-level conflicts, inferential dependencies, and conclusion acceptability. Contribution/Results: Our method significantly outperforms chain-of-thought baselines in conflict resolution accuracy. Explanation-aware training improves cross-scenario generalization accuracy by over 23%. Moreover, it generates traceable, verifiable argumentative paths—enhancing transparency and mitigating the LLM black-box problem.

Technology Category

• Knowledge Representation and Reasoning: Argumentation
• Natural Language Processing: Discourse, Pragmatics & Argument Mining
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

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.

Problem

• LLMs struggle with conflict resolution from incomplete information
• Abstract argumentation framework enhances conflict-solving capabilities
• Process explanations improve model generalization and transparency

Innovation

• Integrating abstract argumentation framework with language models
• Fine-tuning models on argument acceptability computation dataset
• Using process explanations to enhance generalization and transparency