一作ACL 2026Findings· Findings of ACL
A rg B ench: Benchmarking LLM s on Computational Argumentation Tasks
Yamen Ajjour · Carlotta Quensel · Nedim Lipka · Henning Wachsmuth
摘要
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 evalu...