Dynamic Knowledge Integration for Evidence-Driven Counter-Argument Generation with Large Language Models

This paper investigates the role of dynamic external knowledge integration in improving counter-argument generation using Large Language Models (LLMs).While LLMs have shown promise in argumentative tasks, their tendency to generate lengthy, potentially nonfactual responses highlights the need for more controlled and evidence-based approaches.We introduce a reconstructed and manually curated dataset of argument and counter-argument pairs specifically designed to balance argumentative complexity with evaluative feasibility.We also propose a new LLM-as-a-Judge evaluation methodology that shows a stronger correlation with human judgments compared to traditional reference-based metrics.Our experimental results demonstrate that integrating dynamic external knowledge from the web significantly improves the quality of generated counter-arguments, particularly in terms of relatedness, persuasiveness, and factuality.The findings suggest that combining LLMs with real-time external knowledge retrieval offers a promising direction for developing more effective and reliable counter-argumentation systems.Data and code are publicly available. 1