Sharpe Ratio-Guided Active Learning for Preference Optimization in RLHF

• URL: http://arxiv.org/abs/2503.22137v1
• Date: Fri, 28 Mar 2025 04:22:53 GMT
• Title: Sharpe Ratio-Guided Active Learning for Preference Optimization in RLHF
• Authors: Syrine Belakaria, Joshua Kazdan, Charles Marx, Chris Cundy, Willie Neiswanger, Sanmi Koyejo, Barbara E. Engelhardt, Stefano Ermon,
• Abstract summary: We propose an active learning approach to efficiently select prompt and preference pairs.<n>Our method evaluates the gradients of all potential preference annotations to assess their impact on model updates.<n> Experimental results demonstrate that our method outperforms the baseline by up to 5% in win rates against the chosen completion.
• Score: 67.48004037550064
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Reinforcement learning from human feedback (RLHF) has become a cornerstone of the training and alignment pipeline for large language models (LLMs). Recent advances, such as direct preference optimization (DPO), have simplified the preference learning step. However, collecting preference data remains a challenging and costly process, often requiring expert annotation. This cost can be mitigated by carefully selecting the data points presented for annotation. In this work, we propose an active learning approach to efficiently select prompt and preference pairs using a risk assessment strategy based on the Sharpe Ratio. To address the challenge of unknown preferences prior to annotation, our method evaluates the gradients of all potential preference annotations to assess their impact on model updates. These gradient-based evaluations enable risk assessment of data points regardless of the annotation outcome. By leveraging the DPO loss derivations, we derive a closed-form expression for computing these Sharpe ratios on a per-tuple basis, ensuring our approach remains both tractable and computationally efficient. We also introduce two variants of our method, each making different assumptions about prior information. Experimental results demonstrate that our method outperforms the baseline by up to 5% in win rates against the chosen completion with limited human preference data across several language models and real-world datasets.

Related papers

• Active Learning for Direct Preference Optimization [59.84525302418018]
  Direct preference optimization (DPO) is a form of reinforcement learning from human feedback. We propose an active learning framework for DPO, which can be applied to collect human feedback online or to choose the most informative subset of already collected feedback offline.
  arXiv  Detail & Related papers  (2025-03-03T00:36:31Z)
• Preference learning made easy: Everything should be understood through win rate [25.849945888898997]
  This work presents a framework to understand preference learning starting from the sampling of pairwise preference data. First, we prove that the only evaluation of a generative model that respects both preferences and prevalences in the data distribution is a form of win rate. We then analyze preference learning methods as win rate optimization (WRO) or non-WRO.
  arXiv  Detail & Related papers  (2025-02-14T19:01:34Z)
• Uncertainty-Penalized Direct Preference Optimization [52.387088396044206]
  We develop a pessimistic framework for DPO by introducing preference uncertainty penalization schemes. The penalization serves as a correction to the loss which attenuates the loss gradient for uncertain samples. We show improved overall performance compared to vanilla DPO, as well as better completions on prompts from high-uncertainty chosen/rejected responses.
  arXiv  Detail & Related papers  (2024-10-26T14:24:37Z)
• Reward-Augmented Data Enhances Direct Preference Alignment of LLMs [63.32585910975191]
  We introduce reward-conditioned Large Language Models (LLMs) that learn from the entire spectrum of response quality within the dataset.<n>We propose an effective yet simple data relabeling method that conditions the preference pairs on quality scores to construct a reward-augmented dataset.
  arXiv  Detail & Related papers  (2024-10-10T16:01:51Z)
• Hindsight Preference Learning for Offline Preference-based Reinforcement Learning [22.870967604847458]
  Offline preference-based reinforcement learning (RL) focuses on optimizing policies using human preferences between pairs of trajectory segments selected from an offline dataset. We propose to model human preferences using rewards conditioned on future outcomes of the trajectory segments. Our proposed method, Hindsight Preference Learning (HPL), can facilitate credit assignment by taking full advantage of vast trajectory data available in massive unlabeled datasets.
  arXiv  Detail & Related papers  (2024-07-05T12:05:37Z)
• Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback [110.16220825629749]
  Learning from preference feedback has emerged as an essential step for improving the generation quality and performance of modern language models. In this work, we identify four core aspects of preference-based learning: preference data, learning algorithm, reward model, and policy training prompts. Our findings indicate that all aspects are important for performance, with better preference data leading to the largest improvements.
  arXiv  Detail & Related papers  (2024-06-13T16:17:21Z)
• Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks [58.469818546042696]
  We study the sample efficiency of OPE with human preference and establish a statistical guarantee for it. By appropriately selecting the size of a ReLU network, we show that one can leverage any low-dimensional manifold structure in the Markov decision process.
  arXiv  Detail & Related papers  (2023-10-16T16:27:06Z)
• Optimal Sample Selection Through Uncertainty Estimation and Its Application in Deep Learning [22.410220040736235]
  We present a theoretically optimal solution for addressing both coreset selection and active learning. Our proposed method, COPS, is designed to minimize the expected loss of a model trained on subsampled data.
  arXiv  Detail & Related papers  (2023-09-05T14:06:33Z)

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.