Lune

ACL Findings2025

Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst

Hongru Wang, Deng Cai, Wanjun Zhong, Shijue Huang, Jeff Z. Pan, Zeming Liu, Kam-Fai Wong

Abstract

Inference-time scaling has attracted much attention which significantly enhance the performance of Large Language Models (LLMs) in complex reasoning tasks by increasing the length of Chain-of-Thought. These longer intermediate reasoning rationales embody various meta-reasoning skills in human cognition, such as reflection and decomposition, being difficult to create and acquire. In this work, we introduce Self-Reasoning Language Model (SRLM), where the model itself can synthesize longer CoT data and iteratively improve performance through self-training. By incorporating a few demonstration examples (i.e., 1,000 samples) on how to unfold hidden reasoning chains from existing responses, which act as a reasoning catalyst, we demonstrate that SRLM not only enhances the model's initial performance but also ensures more stable and consistent improvements in subsequent iterations. Our proposed SRLM achieves an average absolute improvement of more than +2.5 points across five reasoning tasks: MMLU, GSM8K, ARC-C, Hel-laSwag, and BBH on two backbone models. Moreover, it brings more improvements with more times of sampling during inference, such as absolute +7.89 average improvement with 64 sampling times, revealing the in-depth, diverse and creative reasoning paths in SRLM against the strong baseline.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

3 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Self-Consistency Improves Chain of Thought Reasoning in Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Chain-of-Thought Prompting Elicits Reasoning in Large Language Models cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
  • WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions cites Measuring Massive Multitask Language Understanding
  • Dynamic Early Exit in Reasoning Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Self-Rewarding Language Models cites Measuring Massive Multitask Language Understanding
  • SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking cites Dynamic Early Exit in Reasoning Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers3

  1. Dynamic Early Exit in Reasoning ModelsChenxu Yang, Qingyi Si, Yongjie Duan, Zheliang Zhu et al.ICLR 2026 · 250 citations
  2. SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive ThinkingWeiyang Huang, Xuefeng Bai, Kehai Chen, Xinyang Chen et al.ACL 2026 · 3 citations
  3. NILE: Internal Consistency Alignment in Large Language ModelsMinda Hu, Qiyuan Zhang, Yufei Wang, Bowei He et al.EMNLP 2025

Builds on21

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. Measuring Massive Multitask Language UnderstandingDan Hendrycks, Collin Burns, Steven Basart, Andy Zou et al.ICLR 2021 · 7,905 citations
  3. WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex InstructionsCan Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng et al.ICLR 2024 · 1,206 citations
  4. Self-Consistency Improves Chain of Thought Reasoning in Language ModelsXuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le et al.ICLR 2023 · 681 citations
  5. Self-Rewarding Language ModelsWeizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho, Xian Li et al.ICML 2024 · 569 citations

Related papers

  1. The Impact of Reasoning Step Length on Large Language ModelsMingyu Jin, Qinkai Yu, Dong Shu, Haiyan Zhao et al.ACL Findings 2024 · 39 citations
  2. When More is Less: Understanding Chain-of-Thought Length in LLMsYuyang Wu, Yifei Wang, Ziyu Ye, Tianqi Du et al.ICLR 2026 · 225 citations
  3. Demystifying Long Chain-of-Thought ReasoningShiming Yang, Yuxuan Tong, Xinyao Niu, Graham Neubig et al.ICML 2025
  4. Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMsHaritz Puerto, Tilek Chubakov, Xiaodan Zhu, Harish Tayyar Madabushi et al.ACL 2025 · 13 citations
  5. T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference ScalingZhenyu Hou, Xin Lv, Rui Lu, Jiajie Zhang et al.ICML 2025
Dusk over the sea between two cliffs drawn in fine vertical lines