Difficulty-Based Preference Data Selection by DPO Implicit Reward Gap
Aligning large language models (LLMs) with human preferences is a critical challenge in AI research. While methods like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) are widely used, they often rely on large, costly preference datasets. The current work lacks methods for high-quality data selection specifically for preference data. In this work, we introduce a novel difficulty-based data selection strategy for preference datasets, grounded in the DPO implicit reward mechanism. By selecting preference data examples with smaller DPO implicit reward gaps, which are indicative of more challenging cases, we improve data efficiency and model alignment. Our approach consistently outperforms five strong baselines across multiple datasets and alignment tasks, achieving superior performance with only 10\% of the original data. This principled, efficient selection method offers a promising solution for scaling LLM alignment with limited resources.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
Curriculum-RLAIF: Curriculum Alignment with Reinforcement Learning from AI Feedback
Reward models trained with conventional Reinforcement Learning from AI Feedback (RLAIF) methods suffer from limited generalizability, which hinders the alignment performance of the policy model during reinforcement learn…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)ImplicitRM: Unbiased Reward Modeling from Implicit Preference Data for LLM alignment
Reward modeling represents a long-standing challenge in reinforcement learning from human feedback (RLHF) for aligning language models. Current reward modeling is heavily contingent upon experimental feedback data with h…
Reinforcement LearningRoVRM: A Robust Visual Reward Model Optimized via Auxiliary Textual Preference Data
Large vision-language models (LVLMs) often fail to align with human preferences, leading to issues like generating misleading content without proper visual context (also known as hallucination). A promising solution to t…
HallucinationSeRA: Self-Reviewing and Alignment of Large Language Models using Implicit Reward Margins
Direct alignment algorithms (DAAs), such as direct preference optimization (DPO), have become popular alternatives for Reinforcement Learning from Human Feedback (RLHF) due to their simplicity, efficiency, and stability.…
Instruction FollowingRevisiting Self-Play Preference Optimization: On the Role of Prompt Difficulty
Self-play preference optimization has emerged as a prominent paradigm for aligning large language models (LLMs). It typically involves a language model to generate on-policy responses for prompts and a reward model (RM) …