Beyond Sparse Rewards: Enhancing Reinforcement Learning with Language Model Critique in Text Generation

• URL: http://arxiv.org/abs/2401.07382v2
• Date: Mon, 19 Feb 2024 18:19:20 GMT
• Title: Beyond Sparse Rewards: Enhancing Reinforcement Learning with Language Model Critique in Text Generation
• Authors: Meng Cao, Lei Shu, Lei Yu, Yun Zhu, Nevan Wichers, Yinxiao Liu, Lei Meng
• Abstract summary: Reinforcement learning can align language models with non-differentiable reward signals, such as human preferences. This paper introduces a novel framework that utilizes the critique capability of Large Language Models to produce intermediate-step rewards.
• Score: 29.6763730290473
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward for an entire output. This sparsity of rewards can lead to inefficient and unstable learning. To address this challenge, our paper introduces an novel framework that utilizes the critique capability of Large Language Models (LLMs) to produce intermediate-step rewards during RL training. Our method involves coupling a policy model with a critic language model, which is responsible for providing comprehensive feedback of each part of the output. This feedback is then translated into token or span-level rewards that can be used to guide the RL training process. We investigate this approach under two different settings: one where the policy model is smaller and is paired with a more powerful critic model, and another where a single language model fulfills both roles. We assess our approach on three text generation tasks: sentiment control, language model detoxification, and summarization. Experimental results show that incorporating artificial intrinsic rewards significantly improve both sample efficiency and the overall performance of the policy model, supported by both automatic and human evaluation.

Related papers

• Self-Evolved Reward Learning for LLMs [45.6910747154447]
  Reinforcement Learning from Human Feedback (RLHF) is a crucial technique for aligning language models with human preferences. We propose Self-Evolved Reward Learning (SER), a novel approach where the RM generates additional training data to iteratively improve itself. Our results demonstrate that even with limited human-annotated data, learning from self-feedback can robustly enhance RM performance.
  arXiv  Detail & Related papers  (2024-11-01T07:29:03Z)
• RewardBench: Evaluating Reward Models for Language Modeling [100.28366840977966]
  We present RewardBench, a benchmark dataset and code-base for evaluation of reward models. The dataset is a collection of prompt-chosen-rejected trios spanning chat, reasoning, and safety. On the RewardBench leaderboard, we evaluate reward models trained with a variety of methods.
  arXiv  Detail & Related papers  (2024-03-20T17:49:54Z)
• Is Crowdsourcing Breaking Your Bank? Cost-Effective Fine-Tuning of Pre-trained Language Models with Proximal Policy Optimization [18.75866961339424]
  ChatGPT has highlighted the potential of reinforcement learning from human feedback. To reduce labor costs, we propose a self-supervised text ranking approach.
  arXiv  Detail & Related papers  (2024-02-28T12:24:07Z)
• 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)
• Secrets of RLHF in Large Language Models Part II: Reward Modeling [134.97964938009588]
  We introduce a series of novel methods to mitigate the influence of incorrect and ambiguous preferences in the dataset. We also introduce contrastive learning to enhance the ability of reward models to distinguish between chosen and rejected responses.
  arXiv  Detail & Related papers  (2024-01-11T17:56:59Z)
• SALMON: Self-Alignment with Instructable Reward Models [80.83323636730341]
  This paper presents a novel approach, namely SALMON, to align base language models with minimal human supervision. We develop an AI assistant named Dromedary-2 with only 6 exemplars for in-context learning and 31 human-defined principles.
  arXiv  Detail & Related papers  (2023-10-09T17:56:53Z)
• Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models [24.107358120517336]
  In this work, we adopt a novel perspective wherein a pre-trained language model is itself simultaneously a policy, reward function, and transition function. An immediate consequence of this is that reward learning and language model fine-tuning can be performed jointly and directly, without requiring any further downstream policy optimization.
  arXiv  Detail & Related papers  (2023-05-19T06:21:15Z)
• SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluation [54.66399120084227]
  Language models trained on large-scale corpora can generate remarkably fluent results in open-domain dialogue. For the persona-based dialogue generation task, consistency and coherence are great challenges for language models. A two-stage SimOAP strategy is proposed, i.e., over-sampling and post-evaluation.
  arXiv  Detail & Related papers  (2023-05-18T17:23:00Z)
• Training Language Models with Language Feedback at Scale [50.70091340506957]
  We introduce learning from Language Feedback (ILF), a new approach that utilizes more informative language feedback. ILF consists of three steps that are applied iteratively: first, conditioning the language model on the input, an initial LM output, and feedback to generate refinements. We show theoretically that ILF can be viewed as Bayesian Inference, similar to Reinforcement Learning from human feedback.
  arXiv  Detail & Related papers  (2023-03-28T17:04:15Z)
• Chain of Hindsight Aligns Language Models with Feedback [62.68665658130472]
  We propose a novel technique, Chain of Hindsight, that is easy to optimize and can learn from any form of feedback, regardless of its polarity. We convert all types of feedback into sequences of sentences, which are then used to fine-tune the model. By doing so, the model is trained to generate outputs based on feedback, while learning to identify and correct negative attributes or errors.
  arXiv  Detail & Related papers  (2023-02-06T10:28:16Z)

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.