Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF

• URL: http://arxiv.org/abs/2401.16335v1
• Date: Mon, 29 Jan 2024 17:43:42 GMT
• Title: Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF
• Authors: Banghua Zhu, Michael I. Jordan and Jiantao Jiao
• Abstract summary: Reinforcement Learning from Human Feedback (RLHF) is a technique that aligns language models closely with human-centric values. It is observed that the performance of the reward model degrades after one epoch of training, and optimizing too much against the learned reward model eventually hinders the true objective. This paper delves into these issues, leveraging the theoretical insights to design improved reward learning algorithm termed 'Iterative Data Smoothing' (IDS)
• Score: 79.98542868281471
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique that aligns language models closely with human-centric values. The initial phase of RLHF involves learning human values using a reward model from ranking data. It is observed that the performance of the reward model degrades after one epoch of training, and optimizing too much against the learned reward model eventually hinders the true objective. This paper delves into these issues, leveraging the theoretical insights to design improved reward learning algorithm termed 'Iterative Data Smoothing' (IDS). The core idea is that during each training epoch, we not only update the model with the data, but also update the date using the model, replacing hard labels with soft labels. Our empirical findings highlight the superior performance of this approach over the traditional methods.

Related papers

• Self-Taught Evaluators [77.92610887220594]
  We present an approach that aims to im-proves without human annotations, using synthetic training data only. Our Self-Taught Evaluator can improve a strong LLM from 75.4 to 88.3 on RewardBench.
  arXiv  Detail & Related papers  (2024-08-05T17:57:02Z)
• Weak Reward Model Transforms Generative Models into Robust Causal Event Extraction Systems [17.10762463903638]
  We train evaluation models to approximate human evaluation, achieving high agreement. We propose a weak-to-strong supervision method that uses a fraction of the annotated data to train an evaluation model.
  arXiv  Detail & Related papers  (2024-06-26T10:48:14Z)
• Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment [65.15914284008973]
  We propose to leverage an Inverse Reinforcement Learning (IRL) technique to simultaneously build an reward model and a policy model. We show that the proposed algorithms converge to the stationary solutions of the IRL problem. Our results indicate that it is beneficial to leverage reward learning throughout the entire alignment process.
  arXiv  Detail & Related papers  (2024-05-28T07:11:05Z)
• Towards Understanding the Influence of Reward Margin on Preference Model Performance [8.891183078634786]
  This study introduces a novel method to estimate the preference differences without the need for detailed, exhaustive labels from human annotators. Our experimental results provide empirical evidence that incorporating margin values into the training process significantly improves the effectiveness of reward models.
  arXiv  Detail & Related papers  (2024-04-07T12:10:04Z)
• 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)
• Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble [67.4269821365504]
  Reinforcement Learning from Human Feedback (RLHF) is a widely adopted approach for aligning large language models with human values. However, RLHF relies on a reward model that is trained with a limited amount of human preference data. We contribute a reward ensemble method that allows the reward model to make more accurate predictions.
  arXiv  Detail & Related papers  (2024-01-30T00:17:37Z)
• 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)
• 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)
• The History and Risks of Reinforcement Learning and Human Feedback [0.16843915833103415]
  Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models easier to use and more effective. A core piece of the RLHF process is the training and utilization of a model of human preferences that acts as a reward function for optimization. RLHF reward models are often cited as being central to achieving performance, yet very few descriptors of capabilities, evaluations, training methods, or open-source models exist.
  arXiv  Detail & Related papers  (2023-10-20T15:45:16Z)

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.