Data-adaptive Safety Rules for Training Reward Models

• URL: http://arxiv.org/abs/2501.15453v2
• Date: Tue, 28 Jan 2025 06:35:32 GMT
• Title: Data-adaptive Safety Rules for Training Reward Models
• Abstract summary: Reinforcement Learning from Human Feedback (RLHF) is commonly employed to tailor models to human preferences.<n>In this paper, we propose a dynamic method that adaptively selects the most important rules for each response pair.<n>As of January 25, 2025, our model achieved the highest safety performance on the leaderboard, surpassing various larger models.
• Score: 9.172858508920696
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement Learning from Human Feedback (RLHF) is commonly employed to tailor models to human preferences, especially to improve the safety of outputs from large language models (LLMs). Traditionally, this method depends on selecting preferred responses from pairs. However, due to the variability in human opinions and the challenges in directly comparing two responses, there is an increasing trend towards fine-grained annotation approaches that evaluate responses using multiple targeted metrics or rules. The challenge lies in efficiently choosing and applying these rules to handle the diverse range of preference data. In this paper, we propose a dynamic method that adaptively selects the most important rules for each response pair. We introduce a mathematical framework that utilizes the maximum discrepancy across paired responses and demonstrate theoretically that this approach maximizes the mutual information between the rule-based annotations and the underlying true preferences. We then train an 8B reward model using this adaptively labeled preference dataset and assess its efficacy using RewardBench. As of January 25, 2025, our model achieved the highest safety performance on the leaderboard, surpassing various larger models.

Related papers

• Multimodal Large Language Models with Adaptive Preference Optimization for Sequential Recommendation [60.33386541343322]
  We propose a Multimodal Large Language Models framework that integrates Hardness-aware and Noise-regularized preference optimization for Recommendation (HaNoRec)<n>Specifically, HaNoRec dynamically adjusts optimization weights based on both the estimated hardness of each training sample and the policy model's real-time responsiveness.
  arXiv  Detail & Related papers  (2025-11-24T04:10:46Z)
• Slow Thinking for Sequential Recommendation [88.46598279655575]
  We present a novel slow thinking recommendation model, named STREAM-Rec. Our approach is capable of analyzing historical user behavior, generating a multi-step, deliberative reasoning process, and delivering personalized recommendations. In particular, we focus on two key challenges: (1) identifying the suitable reasoning patterns in recommender systems, and (2) exploring how to effectively stimulate the reasoning capabilities of traditional recommenders.
  arXiv  Detail & Related papers  (2025-04-13T15:53:30Z)
• More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment [80.04449725137177]
  Direct Preference Optimization (DPO) has emerged as a simple, yet effective alternative to reinforcement learning from human feedback. Our study reveals a striking, safety-specific phenomenon associated with DPO alignment. Using solely self-generated responses for both chosen and rejected pairs significantly outperforms configurations that incorporate responses from stronger models.
  arXiv  Detail & Related papers  (2025-04-03T00:36:40Z)
• From Demonstrations to Rewards: Alignment Without Explicit Human Preferences [55.988923803469305]
  In this paper, we propose a fresh perspective on learning alignment based on inverse reinforcement learning principles. Instead of relying on large preference data, we directly learn the reward model from demonstration data.
  arXiv  Detail & Related papers  (2025-03-15T20:53:46Z)
• On-the-fly Preference Alignment via Principle-Guided Decoding [27.50204023448716]
  We introduce On-the-fly Preference Alignment via Principle-Guided Decoding (OPAD) to align model outputs with human preferences during inference. OPAD achieves competitive or superior performance in both general and personalized alignment tasks.
  arXiv  Detail & Related papers  (2025-02-20T02:23:09Z)
• Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling [87.17041933863041]
  We introduce a Response-conditioned Bradley-Terry (Rc-BT) model that enhances the reward model's capability in length bias mitigating and length instruction following. We also propose the Rc-DPO algorithm to leverage the Rc-BT model for direct policy optimization (DPO) of large language models.
  arXiv  Detail & Related papers  (2025-02-02T14:50:25Z)
• Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes [50.544186914115045]
  Large language models (LLMs) are increasingly embedded in everyday applications.<n> Ensuring their alignment with the diverse preferences of individual users has become a critical challenge.<n>We present a novel framework for few-shot steerable alignment.
  arXiv  Detail & Related papers  (2024-12-18T16:14:59Z)
• Beyond the Binary: Capturing Diverse Preferences With Reward Regularization [15.518838657050173]
  We argue that this reliance on binary choices does not capture the broader, aggregate preferences of the target user in real-world tasks.<n>We introduce a simple yet effective method that augments existing binary preference datasets with synthetic preference judgments to estimate potential user disagreement.
  arXiv  Detail & Related papers  (2024-12-05T02:35:46Z)
• Comparison-based Active Preference Learning for Multi-dimensional Personalization [7.349038301460469]
  Large language models (LLMs) have shown remarkable success, but aligning them with human preferences remains a core challenge.<n>Recent studies have explored multi-dimensional personalization, which aims to enable models to generate responses personalized to explicit preferences.<n>We propose Active Multi-dimensional Preference Learning (AMPLe), designed to capture implicit user preferences from interactively collected comparative feedback.
  arXiv  Detail & Related papers  (2024-11-01T11:49:33Z)
• Optimal Design for Reward Modeling in RLHF [83.3614658277817]
  We formalize the reward training model in Reinforcement Learning from Human Feedback. We frame the selection of an effective dataset as a simple regret minimization task. We derive bounds on the simple regret under appropriate assumptions.
  arXiv  Detail & Related papers  (2024-10-22T14:36:44Z)
• Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning [12.742158403867002]
  Reinforcement Learning from Human Feedback is a powerful paradigm for aligning foundation models to human values and preferences. Current RLHF techniques cannot account for the naturally occurring differences in individual human preferences across a diverse population. We develop a class of multimodal RLHF methods to address the need for pluralistic alignment.
  arXiv  Detail & Related papers  (2024-08-19T15:18:30Z)
• Adaptive Preference Scaling for Reinforcement Learning with Human Feedback [103.36048042664768]
  Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values. We propose a novel adaptive preference loss, underpinned by distributionally robust optimization (DRO) Our method is versatile and can be readily adapted to various preference optimization frameworks.
  arXiv  Detail & Related papers  (2024-06-04T20:33:22Z)
• Direct Preference Optimization With Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences [14.686788596611246]
  Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values.<n>Recent alternatives such as Direct Preference Optimization (DPO) simplify this pipeline by directly optimizing on preferences.<n>We propose a theoretical and algorithmic framework for fairness and personalization for diverse users in generative model alignment.
  arXiv  Detail & Related papers  (2024-05-23T21:25:20Z)
• Online Self-Preferring Language Models [34.22412851864247]
  Online Self-Preferring (OSP) language models learn from self-generated response pairs and self-judged preference strengths. OSP achieves state-of-the-art alignment performance across various metrics in two widely used human preference datasets.
  arXiv  Detail & Related papers  (2024-05-23T02:13:34Z)
• 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)

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.