ReFT: Reasoning with Reinforced Fine-Tuning

• URL: http://arxiv.org/abs/2401.08967v2
• Date: Thu, 27 Jun 2024 15:29:15 GMT
• Title: ReFT: Reasoning with Reinforced Fine-Tuning
• Authors: Trung Quoc Luong, Xinbo Zhang, Zhanming Jie, Peng Sun, Xiaoran Jin, Hang Li,
• Abstract summary: We propose a simple yet effective approach called Reinforced Fine-Tuning (ReFT) to enhance the generalizability of learning LLMs for reasoning. ReFT first warmups the model with SFT, and then employs on-line reinforcement learning, specifically the PPO algorithm in this paper. Experiments on GSM8K, MathQA, and SVAMP datasets show that ReFT significantly outperforms SFT.
• Score: 9.80361828538909
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: One way to enhance the reasoning capability of Large Language Models (LLMs) is to conduct Supervised Fine-Tuning (SFT) using Chain-of-Thought (CoT) annotations. This approach does not show sufficiently strong generalization ability, however, because the training only relies on the given CoT data. In math problem-solving, for example, there is usually only one annotated reasoning path for each question in the training data. Intuitively, it would be better for the algorithm to learn from multiple annotated reasoning paths given a question. To address this issue, we propose a simple yet effective approach called Reinforced Fine-Tuning (ReFT) to enhance the generalizability of learning LLMs for reasoning, with math problem-solving as an example. ReFT first warmups the model with SFT, and then employs on-line reinforcement learning, specifically the PPO algorithm in this paper, to further fine-tune the model, where an abundance of reasoning paths are automatically sampled given the question and the rewards are naturally derived from the ground-truth answers. Extensive experiments on GSM8K, MathQA, and SVAMP datasets show that ReFT significantly outperforms SFT, and the performance can be potentially further boosted by combining inference-time strategies such as majority voting and re-ranking. Note that ReFT obtains the improvement by learning from the same training questions as SFT, without relying on extra or augmented training questions. This indicates a superior generalization ability for ReFT.

Related papers

• 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)
• Recursive Introspection: Teaching Language Model Agents How to Self-Improve [30.086494067593268]
  We develop RISE: Recursive IntroSpEction, an approach for fine-tuning large language models. Our experiments show that RISE enables Llama2, Llama3, and Mistral models to improve themselves with more turns on math reasoning tasks.
  arXiv  Detail & Related papers  (2024-07-25T17:35:59Z)
• Unlock the Correlation between Supervised Fine-Tuning and Reinforcement Learning in Training Code Large Language Models [12.656574142412484]
  We make an attempt to understand the correlation between supervised fine-tuning and reinforcement learning. We find that both atomic and synthetic functions are indispensable for SFT's generalization.
  arXiv  Detail & Related papers  (2024-06-14T03:39:01Z)
• Robust Capped lp-Norm Support Vector Ordinal Regression [85.84718111830752]
  Ordinal regression is a specialized supervised problem where the labels show an inherent order. Support Vector Ordinal Regression, as an outstanding ordinal regression model, is widely used in many ordinal regression tasks. We introduce a new model, Capped $ell_p$-Norm Support Vector Ordinal Regression(CSVOR), that is robust to outliers.
  arXiv  Detail & Related papers  (2024-04-25T13:56:05Z)
• Generative Pre-Trained Transformer for Symbolic Regression Base In-Context Reinforcement Learning [12.660401635672967]
  Finding mathematical formulas from observational data is a major demand of scientific research. FormulaGPT achieves the state-of-the-art performance in fitting ability compared with four baselines.
  arXiv  Detail & Related papers  (2024-04-09T14:08:47Z)
• Dense Reward for Free in Reinforcement Learning from Human Feedback [64.92448888346125]
  We leverage the fact that the reward model contains more information than just its scalar output. We use these attention weights to redistribute the reward along the whole completion. Empirically, we show that it stabilises training, accelerates the rate of learning, and, in practical cases, may lead to better local optima.
  arXiv  Detail & Related papers  (2024-02-01T17:10:35Z)
• Training Chain-of-Thought via Latent-Variable Inference [30.21067593018967]
  Large language models (LLMs) solve problems more accurately and interpretably when instructed to work out the answer step by step using a chain-of-thought'' prompt. Naively combining CoT with supervised tuning requires supervision not just of the correct answers, but also of detailed rationales that lead to those answers. We propose a fine-tuning strategy that tries to maximize the emphmarginal log-likelihood of generating a correct answer using CoT prompting.
  arXiv  Detail & Related papers  (2023-11-28T17:47:32Z)
• Decouple Graph Neural Networks: Train Multiple Simple GNNs Simultaneously Instead of One [60.5818387068983]
  Graph neural networks (GNN) suffer from severe inefficiency. We propose to decouple a multi-layer GNN as multiple simple modules for more efficient training. We show that the proposed framework is highly efficient with reasonable performance.
  arXiv  Detail & Related papers  (2023-04-20T07:21:32Z)
• The Wisdom of Hindsight Makes Language Models Better Instruction Followers [84.9120606803906]
  Reinforcement learning has seen wide success in finetuning large language models to better align with instructions via human feedback. In this paper, we consider an alternative approach: converting feedback to instruction by relabeling the original one and training the model for better alignment in a supervised manner. We propose Hindsight Instruction Relabeling (HIR), a novel algorithm for aligning language models with instructions.
  arXiv  Detail & Related papers  (2023-02-10T12:16:38Z)
• Learning to Ask Conversational Questions by Optimizing Levenshtein Distance [83.53855889592734]
  We introduce a Reinforcement Iterative Sequence Editing (RISE) framework that optimize the minimum Levenshtein distance (MLD) through explicit editing actions. RISE is able to pay attention to tokens that are related to conversational characteristics. Experimental results on two benchmark datasets show that RISE significantly outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-06-30T08:44:19Z)

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.