Active Preference Optimization for Sample Efficient RLHF

• URL: http://arxiv.org/abs/2402.10500v2
• Date: Wed, 5 Jun 2024 15:10:08 GMT
• Title: Active Preference Optimization for Sample Efficient RLHF
• Authors: Nirjhar Das, Souradip Chakraborty, Aldo Pacchiano, Sayak Ray Chowdhury,
• Abstract summary: Reinforcement Learning from Human Feedback (RLHF) is pivotal in aligning Large Language Models with human preferences. Current methods rely on uniformly picking prompt-generation pairs from a dataset of prompt-generations. We develop an active-learning algorithm, $textttAPO$, which enhances model alignment by querying preference data.
• Score: 27.772423917657626
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement Learning from Human Feedback (RLHF) is pivotal in aligning Large Language Models (LLMs) with human preferences. Although aligned generative models have shown remarkable abilities in various tasks, their reliance on high-quality human preference data creates a costly bottleneck in the practical application of RLHF. One primary reason is that current methods rely on uniformly picking prompt-generation pairs from a dataset of prompt-generations, to collect human feedback, resulting in sub-optimal alignment under a constrained budget, which highlights the criticality of adaptive strategies in efficient alignment. Recent works [Mehta et al., 2023, Muldrew et al., 2024] have tried to address this problem by designing various heuristics based on generation uncertainty. However, either the assumptions in [Mehta et al., 2023] are restrictive, or [Muldrew et al., 2024] do not provide any rigorous theoretical guarantee. To address these, we reformulate RLHF within contextual preference bandit framework, treating prompts as contexts, and develop an active-learning algorithm, $\textit{Active Preference Optimization}$ ($\texttt{APO}$), which enhances model alignment by querying preference data from the most important samples, achieving superior performance for small sample budget. We analyze the theoretical performance guarantees of $\texttt{APO}$ under the BTL preference model showing that the suboptimality gap of the policy learned via $\texttt{APO}$ scales as $O(1/\sqrt{T})$ for a budget of $T$. We also show that collecting preference data by choosing prompts randomly leads to a policy that suffers a constant sub-optimality. We perform detailed experimental evaluations on practical preference datasets to validate $\texttt{APO}$'s efficacy over the existing methods, establishing it as a sample-efficient and practical solution of alignment in a cost-effective and scalable manner.

Related papers

• Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework [10.317740844867913]
  We build a simulator based on 472 language model pre-training runs with varying data compositions from the SlimPajama dataset. We observe that even simple acquisition functions can enable principled training decisions across training models from 20M to 1B kernels.
  arXiv  Detail & Related papers  (2025-03-26T22:19:47Z)
• Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization [78.82586283794886]
  We present a new offline alignment algorithm, $chi2$-Preference Optimization ($chi$PO) $chi$PO implements the principle of pessimism in the face of uncertainty via regularization. It is provably robust to overoptimization and achieves sample-complexity guarantees based on single-policy concentrability.
  arXiv  Detail & Related papers  (2024-07-18T11:08:40Z)
• Robust Reinforcement Learning from Corrupted Human Feedback [86.17030012828003]
  Reinforcement learning from human feedback (RLHF) provides a principled framework for aligning AI systems with human preference data. We propose a robust RLHF approach -- $R3M$, which models the potentially corrupted preference label as sparse outliers. Our experiments on robotic control and natural language generation with large language models (LLMs) show that $R3M$ improves robustness of the reward against several types of perturbations to the preference data.
  arXiv  Detail & Related papers  (2024-06-21T18:06:30Z)
• Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF [80.32171988565999]
  We introduce a unified approach to online and offline RLHF -- value-incentivized preference optimization (VPO) VPO regularizes the maximum-likelihood estimate of the reward function with the corresponding value function. Experiments on text summarization and dialog verify the practicality and effectiveness of VPO.
  arXiv  Detail & Related papers  (2024-05-29T17:51:42Z)
• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
  We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences. To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model. Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
  arXiv  Detail & Related papers  (2024-05-26T05:38:50Z)
• $i$REPO: $i$mplicit Reward Pairwise Difference based Empirical Preference Optimization [12.266207199002604]
  Large Language Models (LLM) can sometimes produce outputs that deviate from human expectations. We propose a novel framework named $i$REPO, which utilizes implicit Reward pairwise difference regression for Empirical Preference Optimization. We show that $i$REPO effectively achieves self-alignment using soft-label, self-generated responses and the logit of empirical AI annotators.
  arXiv  Detail & Related papers  (2024-05-24T05:42:11Z)
• Provably Robust DPO: Aligning Language Models with Noisy Feedback [10.523790076060171]
  We introduce a general framework for policy optimization in the presence of random preference flips. We design a novel loss function, which de-bias the effect of noise on average, making a policy trained by minimizing that loss robust to the noise. Our experiments on IMDb sentiment generation and Anthropic's helpful-harmless dataset show that rDPO is robust to noise in preference labels compared to vanilla DPO.
  arXiv  Detail & Related papers  (2024-03-01T09:55:18Z)
• Reinforcement Learning from Human Feedback with Active Queries [67.27150911254155]
  Current reinforcement learning approaches often require a large amount of human-labelled preference data. We propose query-efficient RLHF methods, inspired by the success of active learning. Our experiments show that ADPO, while only making about half of queries for human preference, matches the performance of the state-of-the-art DPO method.
  arXiv  Detail & Related papers  (2024-02-14T18:58:40Z)
• Towards Efficient Exact Optimization of Language Model Alignment [93.39181634597877]
  Direct preference optimization (DPO) was proposed to directly optimize the policy from preference data. We show that DPO derived based on the optimal solution of problem leads to a compromised mean-seeking approximation of the optimal solution in practice. We propose efficient exact optimization (EXO) of the alignment objective.
  arXiv  Detail & Related papers  (2024-02-01T18:51:54Z)
• Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning [23.222448307481073]
  We propose a new practical algorithm for offline reinforcement learning (RL) in complex environments with insufficient data coverage. Our algorithm combines the marginalized importance sampling framework with the actor-critic paradigm. We provide both theoretical analysis and experimental results to validate the effectiveness of our proposed algorithm.
  arXiv  Detail & Related papers  (2023-01-30T07:53:53Z)

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.