Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint

• URL: http://arxiv.org/abs/2401.06081v2
• Date: Mon, 17 Jun 2024 05:52:06 GMT
• Title: Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint
• Authors: Zhipeng Chen, Kun Zhou, Wayne Xin Zhao, Junchen Wan, Fuzheng Zhang, Di Zhang, Ji-Rong Wen,
• Abstract summary: Reinforcement learning (RL) has been widely used in training large language models (LLMs) We propose a new RL method named RLMEC that incorporates a generative model as the reward model. Based on the generative reward model, we design the token-level RL objective for training and an imitation-based regularization for stabilizing RL process.
• Score: 104.53687944498155
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning (RL) has been widely used in training large language models (LLMs) for preventing unexpected outputs, eg reducing harmfulness and errors. However, existing RL methods mostly adopt the instance-level reward, which is unable to provide fine-grained supervision for complex reasoning tasks, and can not focus on the few key tokens that lead to the incorrectness. To address it, we propose a new RL method named RLMEC that incorporates a generative model as the reward model, which is trained by the erroneous solution rewriting task under the minimum editing constraint, and can produce token-level rewards for RL training. Based on the generative reward model, we design the token-level RL objective for training and an imitation-based regularization for stabilizing RL process. And the both objectives focus on the learning of the key tokens for the erroneous solution, reducing the effect of other unimportant tokens. The experiment results on mathematical tasks and question-answering tasks have demonstrated the effectiveness of our approach. Our code and data are available at https://github.com/RUCAIBox/RLMEC.

Related papers

• Exploring RL-based LLM Training for Formal Language Tasks with Programmed Rewards [49.7719149179179]
  This paper investigates the feasibility of using PPO for reinforcement learning (RL) from explicitly programmed reward signals. We focus on tasks expressed through formal languages, such as programming, where explicit reward functions can be programmed to automatically assess quality of generated outputs. Our results show that pure RL-based training for the two formal language tasks is challenging, with success being limited even for the simple arithmetic task.
  arXiv  Detail & Related papers  (2024-10-22T15:59:58Z)
• FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning [18.60627708199452]
  We investigate how to leverage pre-trained visual-language models (VLM) for online Reinforcement Learning (RL) We first identify the problem of reward misalignment when applying VLM as a reward in RL tasks. We introduce a lightweight fine-tuning method, named Fuzzy VLM reward-aided RL (FuRL)
  arXiv  Detail & Related papers  (2024-06-02T07:20:08Z)
• Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning [49.87923965553233]
  Reinforcement Learning can lead to reward over-optimization in large language models. We introduce the Reward from Demonstration (RCfD) to recalibrate the reward objective. We show that RCfD achieves comparable performance to carefully tuned baselines while mitigating ROO.
  arXiv  Detail & Related papers  (2024-04-30T09:57:21Z)
• RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback [24.759613248409167]
  Reward engineering has long been a challenge in Reinforcement Learning research. We propose RL-VLM-F, a method that automatically generates reward functions for agents to learn new tasks. We demonstrate that RL-VLM-F successfully produces effective rewards and policies across various domains.
  arXiv  Detail & Related papers  (2024-02-06T04:06:06Z)
• The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from Human Feedback [5.037876196534672]
  Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) more capable in complex settings. In this paper, we illustrate the causes of this issue, reviewing relevant literature from model-based reinforcement learning, and argue for solutions.
  arXiv  Detail & Related papers  (2023-10-31T21:52:41Z)
• Language Reward Modulation for Pretraining Reinforcement Learning [61.76572261146311]
  We propose leveraging the capabilities of LRFs as a pretraining signal for reinforcement learning. Our VLM pretraining approach, which is a departure from previous attempts to use LRFs, can warmstart sample-efficient learning on robot manipulation tasks.
  arXiv  Detail & Related papers  (2023-08-23T17:37:51Z)
• Is RLHF More Difficult than Standard RL? [31.972393805014903]
  Reinforcement learning from Human Feedback (RLHF) learns from preference signals, while standard Reinforcement Learning (RL) directly learns from reward signals. This paper theoretically proves that, for a wide range of preference models, we can solve preference-based RL directly using existing algorithms and techniques for reward-based RL, with small or no extra costs.
  arXiv  Detail & Related papers  (2023-06-25T03:18:15Z)
• CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning [92.36705236706678]
  "CodeRL" is a new framework for program synthesis tasks through pretrained LMs and deep reinforcement learning. During inference, we introduce a new generation procedure with a critical sampling strategy. For the model backbones, we extended the encoder-decoder architecture of CodeT5 with enhanced learning objectives.
  arXiv  Detail & Related papers  (2022-07-05T02:42:15Z)
• Text Generation with Efficient (Soft) Q-Learning [91.47743595382758]
  Reinforcement learning (RL) offers a more flexible solution by allowing users to plug in arbitrary task metrics as reward. We introduce a new RL formulation for text generation from the soft Q-learning perspective. We apply the approach to a wide range of tasks, including learning from noisy/negative examples, adversarial attacks, and prompt generation.
  arXiv  Detail & Related papers  (2021-06-14T18:48:40Z)

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.