ArgBench: Benchmarking LLMs on Computational Argumentation Tasks

arXiv:2604.17366v1 Announce Type: cross Abstract: Argumentation skills are an essential toolkit for large language models (LLMs). These skills are crucial in various use cases, including self-reflection, debating collaboratively for diverse answers, and countering hate speech. In this paper, we create the first benchmark for a standardized evaluation of LLM-based approaches to computational argumentation, encompassing 33 datasets from previous work in unified form. Using the benchmark, we evalua