让大模型学会重构论点，提升批判性思维能力。
Argument Reconstruction as Supervision for Critical Thinking in LLMs
- 自动生成任意论点的重构结构（GAAR引擎）
- 在7个任务中，训练重构论点的模型表现更优
- 适合想提升模型逻辑推理能力的研究者
为提升大语言模型的批判性思维能力，本文提出一个整体框架。首先，设计了一个自动重构任意论点的引擎（GAAR）；其次，利用该引擎构建了高质量的论点重构数据集Arguinas；最后，验证学习论点重构是否有助于下游批判性思维任务。实验结果表明，在7个批判性思维任务中，经过论点重构训练的模型均优于未训练模型，尤其在使用Arguinas数据集训练时性能提升最显著。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。