Eunho Yang, Sean Welleck, Hyun Ryu, Carolyn Rosé, Gyouk Chu, Gregor Betz
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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. 1 * Equal contribution. † Equal advising. 1 The source code and dataset are available at https://github.com/GyoukChu/Arguinas. 2 A reconstruction is valid if its set of premises deductively implies the conclusion.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2603.17432")
get_code_for_paper("2603.17432")
have("2603.17432")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2603.17432.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2603.17432)
Connect an agent — have() is free.