TinyThinker: Distilling Reasoning through Coarse-to-Fine Knowledge Internalization with Self-Reflection

• URL: http://arxiv.org/abs/2412.08024v2
• Date: Tue, 04 Feb 2025 08:57:04 GMT
• Title: TinyThinker: Distilling Reasoning through Coarse-to-Fine Knowledge Internalization with Self-Reflection
• Authors: Shengmin Piao, Sanghyun Park,
• Abstract summary: Large Language Models exhibit impressive reasoning capabilities across diverse tasks. Efforts to distill these capabilities into smaller models through generated reasoning data may lead to superficial imitation of reasoning process. We propose TinyThinker, a framework introducing two novel approaches.
• Score: 2.379928855453728
• License:
• Abstract: Large Language Models exhibit impressive reasoning capabilities across diverse tasks, motivating efforts to distill these capabilities into smaller models through generated reasoning data. However, direct training on such synthesized reasoning data may lead to superficial imitation of reasoning process, rather than fostering a genuine integration of reasoning capabilities with underlying knowledge. To address this, we propose TinyThinker, a framework introducing two novel approaches. First, we introduce a three-stage process that incrementally guides the student model through the reasoning process, progressively refining knowledge from coarse to fine granularity. Second, we develop a two-phase training framework comprising an initial reasoning acquisition phase followed by a self-reflection phase utilizing self-generated data. Experiments on commonsense reasoning benchmarks demonstrate that TinyThinker achieves superior performance compared to baselines. Ablation studies further validate the effectiveness of each component in our framework. We expect that TinyThinker can be extended to other knowledge-intensive reasoning tasks, offering an alternative strategy for developing effective reasoning capabilities in smaller language models. Codes are available at https://github.com/shengminp/TinyThinker

Related papers

• Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems [92.89673285398521]
  o1-like reasoning systems have demonstrated remarkable capabilities in solving complex reasoning tasks. We introduce an imitate, explore, and self-improve'' framework to train the reasoning model. Our approach achieves competitive performance compared to industry-level reasoning systems.
  arXiv  Detail & Related papers  (2024-12-12T16:20:36Z)
• Can Language Models Learn to Skip Steps? [59.84848399905409]
  We study the ability to skip steps in reasoning. Unlike humans, who may skip steps to enhance efficiency or to reduce cognitive load, models do not possess such motivations. Our work presents the first exploration into human-like step-skipping ability.
  arXiv  Detail & Related papers  (2024-11-04T07:10:24Z)
• Collapse of Self-trained Language Models [0.0]
  We explore the potential of self-training models on their own outputs, akin to how humans learn and build on their previous thoughts and actions. We find that extended self-training of the GPT-2 model leads to a significant degradation in performance, resulting in repetitive and collapsed token output.
  arXiv  Detail & Related papers  (2024-04-02T21:03:37Z)
• Conceptual and Unbiased Reasoning in Language Models [98.90677711523645]
  We propose a novel conceptualization framework that forces models to perform conceptual reasoning on abstract questions. We show that existing large language models fall short on conceptual reasoning, dropping 9% to 28% on various benchmarks. We then discuss how models can improve since high-level abstract reasoning is key to unbiased and generalizable decision-making.
  arXiv  Detail & Related papers  (2024-03-30T00:53:53Z)
• Learning From Correctness Without Prompting Makes LLM Efficient Reasoner [30.203952806009717]
  Large language models (LLMs) have demonstrated outstanding performance across various tasks, yet they still exhibit limitations such as hallucination, unfaithful reasoning, and toxic content. We introduce an intrinsic self-correct reasoning framework for LLMs that eliminates the need for human feedback, external tools, and handcraft prompts.
  arXiv  Detail & Related papers  (2024-03-28T02:12:49Z)
• Learning to Reason and Memorize with Self-Notes [51.17609489687686]
  Large language models have been shown to struggle with multi-step reasoning. We propose a simple method for solving both of these problems by allowing the model to take Self-Notes.
  arXiv  Detail & Related papers  (2023-05-01T14:02:48Z)
• ReAct: Synergizing Reasoning and Acting in Language Models [44.746116256516046]
  We show that large language models (LLMs) can generate both reasoning traces and task-specific actions in an interleaved manner. We apply our approach, named ReAct, to a diverse set of language and decision making tasks. ReAct overcomes issues of hallucination and error propagation prevalent in chain-of-thought reasoning by interacting with a simple Wikipedia API.
  arXiv  Detail & Related papers  (2022-10-06T01:00:32Z)
• Anti-Retroactive Interference for Lifelong Learning [65.50683752919089]
  We design a paradigm for lifelong learning based on meta-learning and associative mechanism of the brain. It tackles the problem from two aspects: extracting knowledge and memorizing knowledge. It is theoretically analyzed that the proposed learning paradigm can make the models of different tasks converge to the same optimum.
  arXiv  Detail & Related papers  (2022-08-27T09:27:36Z)
• Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLU [88.8401599172922]
  We develop a framework based on self-training language models with limited task-specific labels and rationales. We show that the neural model performance can be significantly improved by making it aware of its rationalized predictions.
  arXiv  Detail & Related papers  (2021-09-17T00:36:46Z)
• Social Commonsense Reasoning with Multi-Head Knowledge Attention [24.70946979449572]
  Social Commonsense Reasoning requires understanding of text, knowledge about social events and their pragmatic implications, as well as commonsense reasoning skills. We propose a novel multi-head knowledge attention model that encodes semi-structured commonsense inference rules and learns to incorporate them in a transformer-based reasoning cell.
  arXiv  Detail & Related papers  (2020-10-12T10:24:40Z)

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.