We explore the capability of four open-sourcelarge language models (LLMs) in argumentation mining (AM). We conduct experiments on three different corpora; persuasive essays(PE), argumentative microtexts (AMT) Part 1 and Part 2, based on two argumentation mining sub-tasks: (i) argumentative discourse units classifications (ADUC), and (ii) argumentative relation classification (ARC). This work aims to assess the argumentation capability of open-source LLMs, including Mistral 7B, Mixtral8x7B, LlamA2 7B and LlamA3 8B in both, zero-shot and few-shot scenarios. Our analysis contributes to further assessing computational argumentation with open-source LLMs in future research efforts.
翻译:本文探讨了四种开源大语言模型(LLMs)在论证挖掘(AM)任务中的能力。我们基于两个论证挖掘子任务:(i)论证性话语单元分类(ADUC),以及(ii)论证关系分类(ARC),在三个不同的语料库上进行了实验:说服性论文(PE)、论证性微文本(AMT)第一部分和第二部分。本研究旨在评估开源LLMs(包括Mistral 7B、Mixtral8x7B、Llama 2 7B和Llama 3 8B)在零样本和少样本场景下的论证能力。我们的分析有助于在未来研究中进一步利用开源LLMs评估计算论证。