Efficient Long CoT Reasoning in Small Language Models

• URL: http://arxiv.org/abs/2505.18440v1
• Date: Sat, 24 May 2025 00:22:52 GMT
• Title: Efficient Long CoT Reasoning in Small Language Models
• Authors: Zhaoyang Wang, Jinqi Jiang, Tian Qiu, Hui Liu, Xianfeng Tang, Huaxiu Yao,
• Abstract summary: It is challenging to directly train small language models (SLMs) to emerge long chain-of-thought (CoT) reasoning steps.<n>We propose a simple-yet-effective method to prune unnecessary steps in long CoT, and then employ an on-policy method for the SLM itself to curate valid and useful long CoT training data.
• Score: 26.579760423359673
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent large reasoning models such as DeepSeek-R1 exhibit strong complex problems solving abilities by generating long chain-of-thought (CoT) reasoning steps. It is challenging to directly train small language models (SLMs) to emerge long CoT. Thus, distillation becomes a practical method to enable SLMs for such reasoning ability. However, the long CoT often contains a lot of redundant contents (e.g., overthinking steps) which may make SLMs hard to learn considering their relatively poor capacity and generalization. To address this issue, we propose a simple-yet-effective method to prune unnecessary steps in long CoT, and then employ an on-policy method for the SLM itself to curate valid and useful long CoT training data. In this way, SLMs can effectively learn efficient long CoT reasoning and preserve competitive performance at the same time. Experimental results across a series of mathematical reasoning benchmarks demonstrate the effectiveness of the proposed method in distilling long CoT reasoning ability into SLMs which maintains the competitive performance but significantly reduces generating redundant reasoning steps.

Related papers

• SynAdapt: Learning Adaptive Reasoning in Large Language Models via Synthetic Continuous Chain-of-Thought [8.287063165175667]
  Chain-of-Thought (CoT) reasoning incurs significant time costs due to the generation of discrete CoT tokens (DCoT)<n>Existing Continuous CoT methods are hampered by indirect fine-tuning, limited alignment, or inconsistent targets.<n>We propose textitSynAdapt, an innovative efficient reasoning framework.
  arXiv  Detail & Related papers  (2025-08-01T12:17:35Z)
• AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models [56.063571989395946]
  The reasoning-capable large language models (LLMs) demonstrate strong performance on complex reasoning tasks.<n>Recent approaches attempt to address this challenge by manually deciding when to apply long or short reasoning.<n>We propose Auto Long-Short Reasoning (AutoL2S), a dynamic and model-agnostic framework that enables LLMs to dynamically compress their generated reasoning path.
  arXiv  Detail & Related papers  (2025-05-28T17:59:53Z)
• TACO: Think-Answer Consistency for Optimized Long-Chain Reasoning and Efficient Data Learning via Reinforcement Learning in LVLMs [50.820065021136024]
  DeepSeek R1 has significantly advanced complex reasoning for large language models (LLMs)<n>Recent methods have attempted to replicate R1's reasoning capabilities in multimodal settings.<n>We propose TACO, a novel reinforcement learning algorithm for visual reasoning.
  arXiv  Detail & Related papers  (2025-05-27T06:30:48Z)
• Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering [59.34894142132706]
  Existing work finds that the capability of long CoT reasoning can be efficiently elicited by tuning on only a few examples.<n>This motivates us to investigate whether long CoT reasoning is a general capability for LLMs.<n>We propose GLoRE, a novel representation engineering method to unleash the general long CoT reasoning capabilities of LLMs.
  arXiv  Detail & Related papers  (2025-03-14T11:30:37Z)
• Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models [56.37421741507468]
  Chain-of-Thought (CoT) reasoning has significantly enhanced the performance of large language models (LLMs)<n>We propose a method to identify critical reasoning steps using perplexity as a measure of their importance.
  arXiv  Detail & Related papers  (2025-02-18T20:04:51Z)
• When More is Less: Understanding Chain-of-Thought Length in LLMs [53.77747102201451]
  Large Language Models (LLMs) employ Chain-of-Thought (CoT) reasoning to deconstruct complex problems.<n>This paper argues that longer CoTs are often presumed superior, arguing that longer is not always better.
  arXiv  Detail & Related papers  (2025-02-11T05:28:59Z)
• Markov Chain of Thought for Efficient Mathematical Reasoning [10.678633785012691]
  Chain of Thought (CoT) of multi-step benefits from the logical structure of the reasoning steps and task-specific actions.<n>We conceptualize the standard multi-step CoT as a novel Markov Chain of Thought (MCoT)<n>Our MCoT aims to compress previous reasoning steps into a simplified question, enabling efficient next-step inference.
  arXiv  Detail & Related papers  (2024-10-23T07:53:29Z)
• Break the Chain: Large Language Models Can be Shortcut Reasoners [18.047917626825548]
  Chain-of-Thought (CoT) reasoning utilize complex modules but are hampered by high token consumption, limited applicability, and challenges in thinking. This paper conducts a critical evaluation of CoT prompting, extending beyond arithmetic to include complex logical and commonsense reasoning tasks. We propose the integration of human-likes and shortcuts into language models (LMs) through "break the chain" strategies.
  arXiv  Detail & Related papers  (2024-06-04T14:02:53Z)
• The Impact of Reasoning Step Length on Large Language Models [40.546685248243534]
  Chain of Thought (CoT) is significant in improving the reasoning abilities of large language models. We investigate the correlation between the effectiveness of CoT and the length of reasoning steps in prompts.
  arXiv  Detail & Related papers  (2024-01-10T04:37:38Z)
• Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters [82.84696222087396]
  Chain-of-Thought (CoT) prompting can dramatically improve the multi-step reasoning abilities of large language models (LLMs) We show that CoT reasoning is possible even with invalid demonstrations.
  arXiv  Detail & Related papers  (2022-12-20T05:20:54Z)

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.