Towards Reliable Alignment: Uncertainty-aware RLHF

• URL: http://arxiv.org/abs/2410.23726v1
• Date: Thu, 31 Oct 2024 08:26:51 GMT
• Title: Towards Reliable Alignment: Uncertainty-aware RLHF
• Authors: Debangshu Banerjee, Aditya Gopalan,
• Abstract summary: We show that the fluctuation of reward models can be detrimental to the alignment problem. We show that such policies are more risk-averse in the sense that they are more cautious of uncertain rewards. We use this ensemble of reward models to align language model using our methodology and observe that our empirical findings match our theoretical predictions.
• Score: 14.20181662644689
• License:
• Abstract: Recent advances in aligning Large Language Models with human preferences have benefited from larger reward models and better preference data. However, most of these methodologies rely on the accuracy of the reward model. The reward models used in Reinforcement Learning with Human Feedback (RLHF) are typically learned from small datasets using stochastic optimization algorithms, making them prone to high variability. We illustrate the inconsistencies between reward models empirically on numerous open-source datasets. We theoretically show that the fluctuation of the reward models can be detrimental to the alignment problem because the derived policies are more overfitted to the reward model and, hence, are riskier if the reward model itself is uncertain. We use concentration of measure to motivate an uncertainty-aware, conservative algorithm for policy optimization. We show that such policies are more risk-averse in the sense that they are more cautious of uncertain rewards. We theoretically prove that our proposed methodology has less risk than the vanilla method. We corroborate our theoretical results with experiments based on designing an ensemble of reward models. We use this ensemble of reward models to align a language model using our methodology and observe that our empirical findings match our theoretical predictions.

Related papers

• Evaluating Robustness of Reward Models for Mathematical Reasoning [14.97819343313859]
  We introduce a new design for reliable evaluation of reward models, and to validate this, we construct RewardMATH. We demonstrate that the scores on RewardMATH strongly correlate with the results of optimized policy and effectively estimate reward overoptimization.
  arXiv  Detail & Related papers  (2024-10-02T16:39:58Z)
• Elephant in the Room: Unveiling the Impact of Reward Model Quality in Alignment [50.21842377409232]
  Despite vital role reward models play in alignment, previous works have consistently overlooked their performance. This work first investigates the quality of the widely-used preference dataset, HH-RLHF, and curates a clean version, CHH-RLHF. Based on CHH-RLHF, we benchmark the accuracy of a broad range of reward models used in previous alignment works, unveiling the unreliability of using them both for optimization and evaluation.
  arXiv  Detail & Related papers  (2024-09-26T04:28:35Z)
• Quantile Regression for Distributional Reward Models in RLHF [1.8130068086063336]
  We introduce Quantile Reward Models (QRMs), a novel approach to reward modeling that learns a distribution over rewards instead of a single scalar value. Our method uses quantile regression to estimate a full, potentially multimodal distribution over preferences, providing a more powerful and nuanced representation of preferences. Our experimental results show that QRM outperforms comparable traditional point-estimate models on RewardBench.
  arXiv  Detail & Related papers  (2024-09-16T10:54:04Z)
• Fine-Tuning Language Models with Reward Learning on Policy [68.70065254564642]
  Reinforcement learning from human feedback (RLHF) has emerged as an effective approach to aligning large language models (LLMs) to human preferences. Despite its popularity, (fixed) reward models may suffer from inaccurate off-distribution. We propose reward learning on policy (RLP), an unsupervised framework that refines a reward model using policy samples to keep it on-distribution.
  arXiv  Detail & Related papers  (2024-03-28T10:02:10Z)
• 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)
• Scaling Laws for Reward Model Overoptimization [19.93331579503503]
  We study how the gold reward model score changes as we optimize against the proxy reward model using either reinforcement learning or best-of-$n$ sampling. We also study the effect on this relationship of the size of the reward model dataset, the number of reward model and policy parameters, and the coefficient of the KL penalty added to the reward in the reinforcement learning setup.
  arXiv  Detail & Related papers  (2022-10-19T17:56:10Z)
• Rethinking Missing Data: Aleatoric Uncertainty-Aware Recommendation [59.500347564280204]
  We propose a new Aleatoric Uncertainty-aware Recommendation (AUR) framework. AUR consists of a new uncertainty estimator along with a normal recommender model. As the chance of mislabeling reflects the potential of a pair, AUR makes recommendations according to the uncertainty.
  arXiv  Detail & Related papers  (2022-09-22T04:32:51Z)

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.