PaD: Program-aided Distillation Can Teach Small Models Reasoning Better than Chain-of-thought Fine-tuning

• URL: http://arxiv.org/abs/2305.13888v2
• Date: Wed, 20 Mar 2024 08:37:42 GMT
• Title: PaD: Program-aided Distillation Can Teach Small Models Reasoning Better than Chain-of-thought Fine-tuning
• Authors: Xuekai Zhu, Biqing Qi, Kaiyan Zhang, Xinwei Long, Zhouhan Lin, Bowen Zhou,
• Abstract summary: We propose Program-aided Distillation (PaD), which introduces reasoning programs to suppress the errors in distilled data. We evaluate PaD on arithmetic reasoning, symbolic reasoning, and general ability.
• Score: 20.59775450213501
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While large language models (LLMs) excel in various natural language processing tasks, their huge size and the inaccessibility of parameters present challenges for practical deployment. Previous studies try to distill task-specific ability from LLMs to smaller models, using data synthesis and chain-of-thought (CoT) fine-tuning. However, synthetic CoT data often contains faulty reasoning, which deteriorates the quality of distillation, especially in reasoning capabilities. In this work, we propose Program-aided Distillation (PaD), which introduces reasoning programs to suppress the errors in distilled data, and thus achieves better distillation quality for reasoning tasks. In PaD, we utilize the reasoning program to substitute the CoT, allowing automated error checking of synthetic data. Further, through error injecting and further training, the small distilling model could iteratively self-refine the reasoning. Moreover, we conduct a step-wise beam search by step-by-step verifying to acquire more exact reasoning chains. We evaluate PaD on arithmetic reasoning, symbolic reasoning, and general ability. Experimental results demonstrate that smaller models using PaD can not only outperform certain LLMs~(e.g., LLaMA-1 13B) but also achieve strong improvement over baselines with a significantly smaller scale of parameters and data. The source code is publicly available at https://github.com/Xuekai-Zhu/pad.

Related papers

• LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters! [53.84130385074551]
  Large reasoning models (LRMs) tackle complex reasoning problems by following long chain-of-thoughts (Long CoT) We find that a Large Language model (LLM) can effectively learn Long CoT reasoning through data-efficient supervised fine-tuning (SFT) and parameter-efficient low-rank adaptation (LoRA) With just 17k long CoT training samples, the Qwen2.5-32B-Instruct model achieves significant improvements on a wide range of math and coding benchmarks.
  arXiv  Detail & Related papers  (2025-02-11T08:48:48Z)
• When More is Less: Understanding Chain-of-Thought Length in LLMs [53.77747102201451]
  Chain-of-thought (CoT) reasoning enhances the multi-step reasoning capabilities of large language models (LLMs) However, for most models and tasks, does an increase in CoT length consistently lead to improved reasoning accuracy? In this paper, we observe a nuanced relationship: as the number of reasoning steps increases, performance initially improves but eventually decreases.
  arXiv  Detail & Related papers  (2025-02-11T05:28:59Z)
• O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning [98.3430004984531]
  We propose Length-Harmonizing Fine-Tuning (O1-Pruner) to minimize reasoning overhead while maintaining accuracy. Our code is coming soon at https://github.com/StarDewXXX/O1-Pruner.
  arXiv  Detail & Related papers  (2025-01-22T01:35:11Z)
• Beyond Imitation: Learning Key Reasoning Steps from Dual Chain-of-Thoughts in Reasoning Distillation [24.272384832200522]
  We propose mistaktextbfE-textbfDriven key reasontextbfIng step distillatextbfTion (textbfEDIT) We design prompts to generate dual CoTs data with similar reasoning paths but divergent conclusions. Experiments validate the effectiveness of EDIT across both in-domain and out-of-domain benchmark reasoning datasets.
  arXiv  Detail & Related papers  (2024-05-30T06:32:11Z)
• Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction [75.25114727856861]
  Large language models (LLMs) tend to suffer from deterioration at the latter stage ofSupervised fine-tuning process. We introduce a simple disperse-then-merge framework to address the issue. Our framework outperforms various sophisticated methods such as data curation and training regularization on a series of standard knowledge and reasoning benchmarks.
  arXiv  Detail & Related papers  (2024-05-22T08:18:19Z)
• Can LLMs Separate Instructions From Data? And What Do We Even Mean By That? [60.50127555651554]
  Large Language Models (LLMs) show impressive results in numerous practical applications, but they lack essential safety features. This makes them vulnerable to manipulations such as indirect prompt injections and generally unsuitable for safety-critical tasks. We introduce a formal measure for instruction-data separation and an empirical variant that is calculable from a model's outputs.
  arXiv  Detail & Related papers  (2024-03-11T15:48:56Z)
• Turning Dust into Gold: Distilling Complex Reasoning Capabilities from LLMs by Leveraging Negative Data [15.088675135566646]
  Large Language Models (LLMs) have performed well on various reasoning tasks, but their inaccessibility and numerous parameters hinder wide application in practice. We propose a model specialization framework to distill LLMs with negative samples besides positive ones. We conduct extensive experiments across arithmetic reasoning tasks to demonstrate the role of negative data in distillation from LLM.
  arXiv  Detail & Related papers  (2023-12-20T08:28:36Z)
• Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding [38.11411155621616]
  We study self-training as one of the predominant semi-supervised learning approaches. We present UPET, a novel Uncertainty-aware self-Training framework. We show that UPET achieves a substantial improvement in terms of performance and efficiency.
  arXiv  Detail & Related papers  (2023-10-19T02:18:29Z)
• Distilling Reasoning Capabilities into Smaller Language Models [83.66051257039763]
  Step-by-step reasoning approaches like chain of thought (CoT) have proved to be very effective in inducing reasoning capabilities in large language models. However, the success of the CoT approach is fundamentally tied to the model size, and billion parameter-scale models are often needed to get CoT to work. We propose a knowledge distillation approach that leverages the step-by-step CoT reasoning capabilities of larger models and distills these abilities into smaller models.
  arXiv  Detail & Related papers  (2022-12-01T00:39:56Z)
• Can Pretext-Based Self-Supervised Learning Be Boosted by Downstream Data? A Theoretical Analysis [12.188482172898656]
  Pretext-based self-supervised learning aims to learn the semantic representation via a handcrafted pretext task over unlabeled data. citetlee 2020predicting prove that pretext-based self-supervised learning can effectively reduce the sample complexity of downstream tasks under Conditional Independence (CI) We explore the idea of applying a learnable function to the input to make the CI condition hold.
  arXiv  Detail & Related papers  (2021-03-05T09:53:10Z)

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.