Self-Enhanced Reasoning Training: Activating Latent Reasoning in Small Models for Enhanced Reasoning Distillation

• URL: http://arxiv.org/abs/2502.12744v1
• Date: Tue, 18 Feb 2025 11:02:47 GMT
• Title: Self-Enhanced Reasoning Training: Activating Latent Reasoning in Small Models for Enhanced Reasoning Distillation
• Authors: Yong Zhang, Bingyuan Zhang, Zhitao Li, Ming Li, Ning Cheng, Minchuan Chen, Tao Wei, Jun Ma, Shaojun Wang, Jing Xiao,
• Abstract summary: We show that small models can generate high-quality reasoning paths during sampling, even without chain-of-thought prompting.<n>We propose Self-Enhanced Reasoning Training (SERT), which activates and leverages latent reasoning capabilities in small models.<n> Experiments using OpenAI's GPT-3.5 as the teacher model and GPT-2 models as the student models demonstrate that SERT enhances the reasoning abilities of small models.
• Score: 34.48068572413349
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid advancement of large language models (LLMs) has significantly enhanced their reasoning abilities, enabling increasingly complex tasks. However, these capabilities often diminish in smaller, more computationally efficient models like GPT-2. Recent research shows that reasoning distillation can help small models acquire reasoning capabilities, but most existing methods focus primarily on improving teacher-generated reasoning paths. Our observations reveal that small models can generate high-quality reasoning paths during sampling, even without chain-of-thought prompting, though these paths are often latent due to their low probability under standard decoding strategies. To address this, we propose Self-Enhanced Reasoning Training (SERT), which activates and leverages latent reasoning capabilities in small models through self-training on filtered, self-generated reasoning paths under zero-shot conditions. Experiments using OpenAI's GPT-3.5 as the teacher model and GPT-2 models as the student models demonstrate that SERT enhances the reasoning abilities of small models, improving their performance in reasoning distillation.

Related papers

• Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models [49.598776427454176]
  Large Reasoning Models (LRMs) have gradually become a research hotspot due to their outstanding performance in handling complex tasks.<n>However, with the widespread application of these models, the problem of overthinking has gradually emerged.<n>Various efficient reasoning methods have been proposed, aiming to reduce the length of reasoning paths without compromising model performance and reasoning capability.
  arXiv  Detail & Related papers  (2025-08-04T06:54:31Z)
• ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning [12.83211408922535]
  Reinforcement learning-style post-training improves reasoning by optimizing model outputs based on reward or preference signals.<n> GRPO-style approaches implement this by using self-generated samples labeled by an outcome-based verifier.<n>We propose $textbfSelf-Explanation Policy Optimization (ExPO)$-a simple and modular framework that generates such samples by conditioning on the ground-truth answer.
  arXiv  Detail & Related papers  (2025-07-03T17:44:55Z)
• NaturalThoughts: Selecting and Distilling Reasoning Traces for General Reasoning Tasks [65.70224757972068]
  We select reasoning traces from a strong teacher model based on a large pool of questions from NaturalReasoning.<n>We find that simply scaling up data size with random sampling is a strong baseline with steady performance gains.<n>We find that selecting difficult examples that require more diverse reasoning strategies is more sample-efficient to transfer the teacher model's reasoning skills.
  arXiv  Detail & Related papers  (2025-07-02T17:30:24Z)
• Large Reasoning Models are not thinking straight: on the unreliability of thinking trajectories [0.0]
  Large Language Models (LLMs) trained via Reinforcement Learning (RL) have recently achieved impressive results on reasoning benchmarks.<n>Yet, growing evidence shows that these models often generate longer but ineffective chains of thought (CoTs)<n>We present new evidence of overthinking, where models disregard correct solutions even when explicitly provided, instead continuing to generate unnecessary reasoning steps.
  arXiv  Detail & Related papers  (2025-07-01T12:14:22Z)
• ReasonGRM: Enhancing Generative Reward Models through Large Reasoning Models [9.30148520355391]
  We present ReasonGRM, a three-stage generative reward modeling framework.<n>In the first stage, Zero-RL is used to generate concise, outcome-directed reasoning paths.<n>In the second stage, $Rstar$, which scores reasoning paths based on their generation likelihood.<n>In the final stage, the model is further refined through reinforcement learning to enhance its preference discrimination capabilities.
  arXiv  Detail & Related papers  (2025-06-20T03:10:52Z)
• Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement [101.77467538102924]
  Large reasoning models (LRMs) exhibit overthinking, which hinders efficiency and inflates inference cost.<n>We propose two lightweight methods to enhance LRM efficiency.<n>First, we introduce Efficiency Steering, a training-free activation steering technique that modulates reasoning behavior via a single direction.<n>Second, we develop Self-Rewarded Efficiency RL, a reinforcement learning framework that dynamically balances task accuracy and brevity.
  arXiv  Detail & Related papers  (2025-06-18T17:18:12Z)
• Phi-4-Mini-Reasoning: Exploring the Limits of Small Reasoning Language Models in Math [135.1260782461186]
  Chain-of-Thought (CoT) significantly enhances formal reasoning capabilities in Large Language Models (LLMs) However, improving reasoning in Small Language Models (SLMs) remains challenging due to their limited model capacity. We present a systematic training recipe for SLMs that consists of four steps: (1) large-scale mid-training on diverse distilled long-CoT data, (2) supervised fine-tuning on high-quality long-CoT data, (3) Rollout DPO leveraging a carefully curated preference dataset, and (4) Reinforcement Learning (RL) with Verifiable Reward.
  arXiv  Detail & Related papers  (2025-04-30T00:04:35Z)
• Think Deep, Think Fast: Investigating Efficiency of Verifier-free Inference-time-scaling Methods [39.89239733570008]
  This work conducts a comprehensive analysis of inference-time scaling methods for both reasoning and non-reasoning models. We find that non-reasoning models, even with an extremely high inference budget, still fall substantially behind reasoning models. For reasoning models, majority voting proves to be a robust inference strategy, generally competitive or outperforming other more sophisticated ITC methods.
  arXiv  Detail & Related papers  (2025-04-18T19:32:55Z)
• Leveraging Reasoning Model Answers to Enhance Non-Reasoning Model Capability [16.441081996257576]
  We propose leveraging reasoning-intensive models to improve less computationally demanding, non-reasoning models. We demonstrate consistent improvements across various benchmarks, underscoring the potential of this approach for advancing the ability of models to answer questions directly.
  arXiv  Detail & Related papers  (2025-04-13T16:26:56Z)
• Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning [12.559028963968247]
  We investigate the crucial relationship between a model's reasoning ability and fairness. We find that larger models with stronger reasoning abilities exhibit substantially lower stereotypical bias. We introduce ReGiFT, a novel approach that extracts structured reasoning traces from advanced reasoning models and infuses them into models that lack such capabilities.
  arXiv  Detail & Related papers  (2025-04-08T03:21:51Z)
• Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models [54.04678363287392]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks. Recent advancements in OpenAI o1 and DeepSeek-R1 have further improved performance in System-2 reasoning domains.
  arXiv  Detail & Related papers  (2025-03-20T17:59:38Z)
• Small Models Struggle to Learn from Strong Reasoners [14.895026967556088]
  Small models do not consistently benefit from long chain-of-thought reasoning or distillation from larger models.<n>We propose Mix Distillation, a strategy that balances reasoning complexity by combining long and short CoT examples or reasoning from both larger and smaller models.<n>Our experiments demonstrate that Mix Distillation significantly improves small model reasoning performance compared to training on either data alone.
  arXiv  Detail & Related papers  (2025-02-17T18:56:15Z)
• Enhancing Knowledge Distillation for LLMs with Response-Priming Prompting [1.9461727843485295]
  We propose a set of novel response-priming prompting strategies to enhance the performance of student models.<n>Our approach fine-tunes a smaller Llama 3.1 8B Instruct model by distilling knowledge from a quantized Llama 3.1 405B Instruct teacher model.<n>We find that Ground Truth prompting results in a 55% performance increase on GSM8K for a distilled Llama 3.1 8B Instruct.
  arXiv  Detail & Related papers  (2024-12-18T20:41:44Z)
• DistiLLM: Towards Streamlined Distillation for Large Language Models [53.46759297929675]
  DistiLLM is a more effective and efficient KD framework for auto-regressive language models. DisiLLM comprises two components: (1) a novel skew Kullback-Leibler divergence loss, where we unveil and leverage its theoretical properties, and (2) an adaptive off-policy approach designed to enhance the efficiency in utilizing student-generated outputs.
  arXiv  Detail & Related papers  (2024-02-06T11:10:35Z)
• Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training [49.3242278912771]
  Multimodal reasoning is a challenging task that requires models to reason across multiple modalities to answer questions. Existing approaches have made progress by incorporating language and visual modalities into a two-stage reasoning framework. We propose MC-CoT, a self-consistency training strategy that generates multiple rationales and answers, subsequently selecting the most accurate through a voting process.
  arXiv  Detail & Related papers  (2023-11-23T17:09:48Z)
• First-Step Advantage: Importance of Starting Right in Multi-Step Math Reasoning [11.75364271481855]
  Language models can solve complex reasoning tasks better by learning to generate rationales for their predictions. We observe that smaller models in particular when corrected, can solve a task that they would have otherwise struggled with. We propose QuestCoT, where a smaller model first asks itself how to start, before proceeding with a chain of reasoning.
  arXiv  Detail & Related papers  (2023-11-14T06:45:31Z)
• Ladder-of-Thought: Using Knowledge as Steps to Elevate Stance Detection [73.31406286956535]
  We introduce the Ladder-of-Thought (LoT) for the stance detection task. LoT directs the small LMs to assimilate high-quality external knowledge, refining the intermediate rationales produced. Our empirical evaluations underscore LoT's efficacy, marking a 16% improvement over GPT-3.5 and a 10% enhancement compared to GPT-3.5 with CoT on stance detection task.
  arXiv  Detail & Related papers  (2023-08-31T14:31:48Z)
• Large Language Models Are Reasoning Teachers [9.290757451344673]
  Fine-tune-CoT is a method that generates reasoning samples from very large teacher models to fine-tune smaller models. We find that Fine-tune-CoT enables substantial reasoning capability in small models, far outperforming prompt-based baselines and even the teacher model in many tasks.
  arXiv  Detail & Related papers  (2022-12-20T08:24:45Z)
• Explanations from Large Language Models Make Small Reasoners Better [61.991772773700006]
  We show that our method can consistently and significantly outperform finetuning baselines across different settings. As a side benefit, human evaluation shows that our method can generate high-quality explanations to justify its predictions.
  arXiv  Detail & Related papers  (2022-10-13T04:50:02Z)
• Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations [97.91630330328815]
  We conduct a crowdsourcing study, where participants interact with deception detection models that have been trained to distinguish between genuine and fake hotel reviews. We observe that for a linear bag-of-words model, participants with access to the feature coefficients during training are able to cause a larger reduction in model confidence in the testing phase when compared to the no-explanation control.
  arXiv  Detail & Related papers  (2021-12-17T18:29:56Z)
• On the Efficacy of Small Self-Supervised Contrastive Models without Distillation Signals [44.209171209780365]
  Small models perform quite poorly under the paradigm of self-supervised contrastive learning. Existing methods usually adopt a large off-the-shelf model to transfer knowledge to the small one via knowledge distillation. Despite their effectiveness, distillation-based methods may not be suitable for some resource-restricted scenarios.
  arXiv  Detail & Related papers  (2021-07-30T17:10:05Z)

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.