Unveiling the Mechanisms of Explicit CoT Training: How Chain-of-Thought Enhances Reasoning Generalization

• URL: http://arxiv.org/abs/2502.04667v1
• Date: Fri, 07 Feb 2025 05:21:13 GMT
• Title: Unveiling the Mechanisms of Explicit CoT Training: How Chain-of-Thought Enhances Reasoning Generalization
• Authors: Xinhao Yao, Ruifeng Ren, Yun Liao, Yong Liu,
• Abstract summary: Training large language models with high-quality Chain-of-Thought (CoT) annotations has become a widely adopted strategy.<n>We show that training with CoT markedly improves reasoning generalization, extending it from in-distribution (ID) to both ID and out-of-distribution (OOD) scenarios, while also speeding up convergence.<n>Our findings elucidate the mechanisms underlying explicit CoT training and offer critical insights into tuning strategies for LLMs to achieve robust generalization.
• Score: 9.191236388401226
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Training large language models (LLMs) with high-quality Chain-of-Thought (CoT) annotations has become a widely adopted strategy due to its significant enhancement of reasoning capabilities. To fully comprehend this approach, two questions naturally arise: (Q1) What advantages does training with CoT offer compared to training without CoT? (Q2) If there are advantages, what are the underlying mechanisms of explicit CoT training? Analyzing the advantages and mechanisms of CoT training is challenging due to the many factors involved. To address this, we conduct a detailed analysis using clear and controllable data distributions and, for the first time, reveal that CoT training offers the following advantages: (1) Training with CoT markedly improves reasoning generalization, extending it from in-distribution (ID) to both ID and out-of-distribution (OOD) scenarios, while also speeding up convergence; (2) Even when training with CoT includes a certain range of erroneous reasoning steps, it still enables the model to learn reasoning patterns, leading to systematic generalization. We further explore the underlying mechanisms from a circuit perspective: (1) The data distribution (e.g., ratio $\lambda$ and pattern) plays a crucial role in influencing the model's systematic generalization; (2) CoT training (with two-hop facts) internalizes reasoning into a two-stage generalizing circuit, where the number of stages corresponds to the explicit reasoning steps during training. Our findings elucidate the mechanisms underlying explicit CoT training and offer critical insights into tuning strategies for LLMs to achieve robust generalization.

Related papers

• Chain-of-Thought Prompting for Out-of-Distribution Samples: A Latent-Variable Study [5.236910203359897]
  Chain-of-Thought (CoT) prompting has emerged as a powerful technique to improve in-context learning in large language models. We extend a latent-variable framework for CoT prompting and study its behavior on two prototypical out-of-distribution (OOD) scenarios. Our experiments demonstrate that CoT inference generalizes effectively to OOD samples whose latent variables closely resemble those seen during training, but its performance degrades as this similarity decreases.
  arXiv  Detail & Related papers  (2025-04-17T14:59:29Z)
• The Curse of CoT: On the Limitations of Chain-of-Thought in In-Context Learning [39.613595533503144]
  Chain-of-Thought (CoT) prompting has been widely recognized for its ability to enhance reasoning capabilities in large language models. We show that CoT consistently underperforms direct answering across varying model scales and benchmark complexities. Our analysis uncovers a fundamental explicit-implicit duality driving CoT's performance in pattern-based ICL.
  arXiv  Detail & Related papers  (2025-04-07T13:51:06Z)
• Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1 [53.894789613838654]
  We introduce SEED-Bench-R1, a benchmark designed to evaluate post-training methods for MLLMs in video understanding. It includes intricate real-world videos and complex everyday planning tasks in the format of multiple-choice questions. Using Qwen2-VL-Instruct-7B as a base model, we compare RL with supervised fine-tuning (SFT) Our detailed analysis reveals that RL enhances visual perception but often produces less coherent reasoning chains.
  arXiv  Detail & Related papers  (2025-03-31T17:55:23Z)
• 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)
• Beyond In-Distribution Success: Scaling Curves of CoT Granularity for Language Model Generalization [35.16980045900664]
  Generalization to novel compound tasks under distribution shift is important for deploying transformer-based language models (LMs) This work investigates Chain-of-Thought (CoT) reasoning as a means to enhance OOD generalization.
  arXiv  Detail & Related papers  (2025-02-25T15:04:17Z)
• Demystifying Long Chain-of-Thought Reasoning in LLMs [46.352406501403465]
  Long chains-of-thought (CoTs) enable strategies like backtracking and error correction.<n>Reinforcement learning (RL) has emerged as a crucial method for developing these capabilities.<n>We identify the key factors that enable models to generate long CoT trajectories.
  arXiv  Detail & Related papers  (2025-02-05T17:13:32Z)
• Rethinking Chain-of-Thought from the Perspective of Self-Training [10.722453877596998]
  Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent capabilities in LLMs.<n>We propose a novel CoT framework to improve reasoning performance.<n>Our framework integrates two key components: (i) a task-specific prompt module that optimize the initial reasoning process, and (ii) an adaptive reasoning module that dynamically refines the reasoning process.
  arXiv  Detail & Related papers  (2024-12-14T13:12:50Z)
• RL-STaR: Theoretical Analysis of Reinforcement Learning Frameworks for Self-Taught Reasoner [2.779063752888881]
  Self-taught reasoner (STaR) framework uses reinforcement learning to automatically generate reasoning steps. STaR and its variants have demonstrated empirical success, but a theoretical foundation explaining these improvements is lacking. This work provides a theoretical framework for understanding the effectiveness of reinforcement learning on CoT reasoning and STaR.
  arXiv  Detail & Related papers  (2024-10-31T13:17:53Z)
• Improve Vision Language Model Chain-of-thought Reasoning [86.83335752119741]
  Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. We show that training VLM on short answers does not generalize well to reasoning tasks that require more detailed responses.
  arXiv  Detail & Related papers  (2024-10-21T17:00:06Z)
• Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis [82.51626700527837]
  Chain-of-shift (CoT) is an efficient method that enables the reasoning ability of large language models by augmenting the query using examples with multiple intermediate steps. We show that despite the theoretical success of CoT, it fails to provide an accurate generalization when CoT does.
  arXiv  Detail & Related papers  (2024-10-03T03:12:51Z)
• The mechanistic basis of data dependence and abrupt learning in an in-context classification task [0.3626013617212666]
  We show that specific distributional properties inherent in language control the trade-off or simultaneous appearance of two forms of learning. In-context learning is driven by the abrupt emergence of an induction head, which subsequently competes with in-weights learning. We propose that the sharp transitions in attention-based networks arise due to a specific chain of multi-layer operations necessary to achieve ICL.
  arXiv  Detail & Related papers  (2023-12-03T20:53:41Z)
• 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.