Paper
Argument Reconstruction as Supervision for Critical Thinking in LLMs
Authors
Hyun Ryu, Gyouk Chu, Gregor Betz, Eunho Yang, Carolyn Rose, Sean Welleck
Abstract
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. The source code and dataset will be publicly available.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.17432v1</id>\n <title>Argument Reconstruction as Supervision for Critical Thinking in LLMs</title>\n <updated>2026-03-18T07:17:54Z</updated>\n <link href='https://arxiv.org/abs/2603.17432v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.17432v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>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. The source code and dataset will be publicly available.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n <published>2026-03-18T07:17:54Z</published>\n <arxiv:primary_category term='cs.CL'/>\n <author>\n <name>Hyun Ryu</name>\n </author>\n <author>\n <name>Gyouk Chu</name>\n </author>\n <author>\n <name>Gregor Betz</name>\n </author>\n <author>\n <name>Eunho Yang</name>\n </author>\n <author>\n <name>Carolyn Rose</name>\n </author>\n <author>\n <name>Sean Welleck</name>\n </author>\n </entry>"
}