Argument Reconstruction as Supervision for Critical Thinking in LLMs

• URL: http://arxiv.org/abs/2603.17432v1
• Date: Wed, 18 Mar 2026 07:17:54 GMT
• Title: Argument Reconstruction as Supervision for Critical Thinking in LLMs
• Abstract summary: We propose an engine that automatically reconstructs arbitrary arguments (GAAR)<n>We synthesize a new high-quality argument reconstruction dataset (Arguinas) using the GAAR engine.<n>Our experimental results show that, across seven critical thinking tasks, models trained to learn argument reconstruction outperform models that do not.
• Score: 47.26477494850773
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• ARGUS: Theory-of-Mind Guided Argument Generation with Strategy-Aware Planning and Knowledge Grounding [5.0921317897723215]
  We propose Argus, an agent-based framework that operationalizes classical rhetoric for persuasive writing.<n>At its core, a Theory-of-Mind (ToM) Reasoner constructs an explicit dual mental model of the audience's beliefs and values to guide downstream decisions.<n>We evaluate Argus across three diverse benchmarks using both automated pairwise Elo and LLM-as-judge metrics.
  arXiv  Detail & Related papers  (2026-08-06T02:26:10Z)
• WhisperRec: Latent Reasoning for Efficient Foundation Recommendation Models [51.88075626243057]
  We propose WhisperRec, an efficient latent reasoning framework for foundation recommendation models (FRMs)<n>WhisperRec compresses teacher-generated Chain-of-Thought (CoT) into learnable latent reasoning tokens.<n>We show that WhisperRec consistently outperforms explicit-CoT methods and conventional baselines.
  arXiv  Detail & Related papers  (2026-07-29T08:48:35Z)
• OneReason Technical Report [135.82017930661263]
  We show that generative recommendation models can only benefit from the scaling advantage, while their reasoning ability is hard to activate.<n>We propose OneReason, which includes: (1) strong itemic token perception in pre-training, (2) a three-level cognition-enhanced CoT format for recommendation tasks in SFT, and (3) a specialize-then-unify training recipe in RL.
  arXiv  Detail & Related papers  (2026-06-04T15:04:34Z)
• An LLM-Based System for Argument Mining [0.03499870393443267]
  We present an end-to-end large language model (LLM)-based system for reconstructing arguments from natural language text into abstract argument graphs.<n>The system follows a multi-stage pipeline that progressively identifies argumentative components, selects relevant elements, and uncovers their logical relations.<n>Results show that the system can adequately recover argumentative structures and, when adapted to different annotation schemes, achieve reasonable performance across benchmark datasets.
  arXiv  Detail & Related papers  (2026-05-13T17:13:45Z)
• Structured Reasoning for Large Language Models [59.215789462977206]
  We propose Structured Reasoning (SCR), a framework that decouples reasoning trajectories into explicit, evaluable, and trainable components.<n>SCR substantially improves reasoning efficiency and self-verification.<n>Compared with existing reasoning paradigms, it reduces output token length by up to 50%.
  arXiv  Detail & Related papers  (2026-01-12T04:04:01Z)
• Making Mathematical Reasoning Adaptive [61.45161826629692]
  We propose the AdaR framework to enable adaptive reasoning in large language models (LLMs)<n>AdaR synthesizes logically equivalent queries by varying variable values, and trains models with RLVR on these data to penalize spurious logic.<n> Experimental results demonstrate that AdaR improves robustness and generalization, achieving substantial improvement in mathematical reasoning.
  arXiv  Detail & Related papers  (2025-10-06T09:30:05Z)
• mSCoRe: a $M$ultilingual and Scalable Benchmark for $S$kill-based $Co$mmonsense $Re$asoning [74.97363626515236]
  We propose a textbfMultilingual and Scalable Benchmark for textbfSkill-based textbfCommonsense textbfReasoning (textbfmSCoRe)<n>Our benchmark incorporates three key components that are designed to systematically evaluate LLM's reasoning capabilities.<n>Our results reveal the limitations of such reasoning-reinforced models when confronted with nuanced multilingual general and cultural commonsense.
  arXiv  Detail & Related papers  (2025-08-13T18:59:02Z)
• Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models [49.61246073215651]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks.<n>Recent advancements in OpenAI o1 and DeepSeek-R1 have further improved performance in System-2 reasoning domains.<n>However, they also introduce significant computational overhead due to verbose and redundant outputs.
  arXiv  Detail & Related papers  (2025-03-20T17:59:38Z)
• DeepRAG: Thinking to Retrieve Step by Step for Large Language Models [92.87532210660456]
  We propose DeepRAG, a framework that models retrieval-augmented reasoning as a Markov Decision Process (MDP)<n>By iteratively decomposing queries, DeepRAG dynamically determines whether to retrieve external knowledge or rely on parametric reasoning at each step.<n> Experiments show that DeepRAG improves retrieval efficiency and boosts answer accuracy by 26.4%, demonstrating its effectiveness in enhancing retrieval-augmented reasoning.
  arXiv  Detail & Related papers  (2025-02-03T08:22:45Z)
• ConQRet: Benchmarking Fine-Grained Evaluation of Retrieval Augmented Argumentation with LLM Judges [23.179246872272362]
  Computational argumentation has become increasingly important in today's polarized environment.<n>We propose a new benchmark featuring long and complex human-authored arguments on debated topics, grounded in real-world websites.<n>Our proposed LLM Judges and the ConQRet benchmark can enable rapid progress in computational argumentation.
  arXiv  Detail & Related papers  (2024-12-06T17:35:52Z)
• RL-STaR: Theoretical Analysis of Reinforcement Learning Frameworks for Self-Taught Reasoner [2.5903660653548366]
  Self-taught reasoner (STaR) uses reinforcement learning to automatically generate reasoning steps.<n> STaR and its variants have demonstrated empirical success, but a theoretical foundation explaining these improvements is lacking.<n>This work provides a theoretical framework for understanding the effectiveness of reinforcement learning on CoT reasoning and STaR.
  arXiv  Detail & Related papers  (2024-10-31T13:17:53Z)
• Contextualizing Argument Quality Assessment with Relevant Knowledge [11.367297319588411]
  SPARK is a novel method for scoring argument quality based on contextualization via relevant knowledge. We devise four augmentations that leverage large language models to provide feedback, infer hidden assumptions, supply a similar-quality argument, or give a counter-argument.
  arXiv  Detail & Related papers  (2023-05-20T21:04:58Z)
• Critical Thinking for Language Models [6.963299759354333]
  This paper takes a first step towards a critical thinking curriculum for neural auto-regressive language models. We generate artificial argumentative texts to train and evaluate GPT-2. We obtain consistent and promising results for NLU benchmarks.
  arXiv  Detail & Related papers  (2020-09-15T15:49:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.