arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.17432cs.CL
收藏

论点重建作为大语言模型批判性思维的监督

Argument Reconstruction as Supervision for Critical Thinking in LLMs

Carnegie Mellon University(卡内基梅隆大学);KAIST(韩国科学技术院);KIT(卡尔斯鲁厄理工学院)

Hyun Ryu, Gyouk Chu, Gregor Betz, Eunho Yang, Carolyn Rose, Sean Welleck

AI总结:

本文提出GAAR引擎和Arguinas数据集,探讨通过论点重建提升大语言模型批判性思维能力,实验显示在七项任务中训练模型表现更优。

摘要:

为了培养批判性思维,人类学习者被训练识别、重建和评估论点。论点重建尤其重要,因为它使论点的隐含推理显性化。然而,不清楚LLM是否能通过学习重建论点来增强批判性思维能力。为此,我们提出一个全面框架,包含三个贡献:(1) 提出GAAR引擎自动重建任意论点;(2) 使用GAAR引擎合成高质量论点重建数据集Arguinas;(3) 调查学习论点重建是否有助于下游批判性思维任务。实验结果表明,在七项批判性思维任务中,训练模型学习论点重建的模型表现优于未训练模型,训练Arguinas数据集时性能提升最大。

英文摘要:

To think critically about arguments, human learners are trained to identify, reconstruct, and evaluate arguments. Argument reconstruction is especially important because it makes an argument's underlying inferences explicit. However, it remains unclear whether LLMs can similarly enhance their critical thinking ability by learning to reconstruct arguments. To address this question, we introduce a holistic framework with three contributions. We (1) propose an engine that automatically reconstructs arbitrary arguments (GAAR), (2) synthesize a new high-quality argument reconstruction dataset (Arguinas) using the GAAR engine, and (3) investigate whether learning argument reconstruction benefits downstream critical thinking tasks. Our experimental results show that, across seven critical thinking tasks, models trained to learn argument reconstruction outperform models that do not, with the largest performance gains observed when training on the proposed Arguinas dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑