# Argument Reconstruction as Supervision for Critical Thinking in LLMs

arXiv: https://arxiv.org/abs/2603.17432 · HTML: https://mlsanity.com/paper/2603.17432/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 14 of its 45 references that are in the map.
- First posted on arXiv 18 Mar 2026.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 14 of 14)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning](https://mlsanity.com/paper/2002.04326/) (2020)
- [Explaining Answers with Entailment Trees](https://mlsanity.com/paper/2104.08661/) (2021)
- [The Argument Reasoning Comprehension Task: Identification and Reconstruction of Implicit Warrants](https://mlsanity.com/paper/1708.01425/) (2017)
- [Critical Thinking for Language Models](https://mlsanity.com/paper/2009.07185/) (2020)
- [Measuring and Improving Persuasiveness of Large Language Models](https://mlsanity.com/paper/2410.02653/) (2024)
- [Finding Convincing Arguments Using Scalable Bayesian Preference Learning](https://mlsanity.com/paper/1806.02418/) (2018)
- [DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Models](https://mlsanity.com/paper/2110.01509/) (2021)
- [Argument Quality Assessment in the Age of Instruction-Following Large Language Models](https://mlsanity.com/paper/2403.16084/) (2024)
- [ARCHE: A Novel Task to Evaluate LLMs on Latent Reasoning Chain Extraction](https://mlsanity.com/paper/2511.12485/) (2025)
- [Detecting Winning Arguments with Large Language Models and Persuasion Strategies](https://mlsanity.com/paper/2601.10660/) (2026)

## Abstract (arXiv)

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.