pith. sign in

arxiv: 2402.10038 · v2 · pith:AABDAKE2new · submitted 2024-02-15 · 💻 cs.CL · cs.AI· cs.CV· cs.LG

RS-DPO: A Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language Models

classification 💻 cs.CL cs.AIcs.CVcs.LG
keywords modelalignmentcontrastivehumanmethodoptimizationpolicypreference
0
0 comments X
read the original abstract

Reinforcement learning from human feedback (RLHF) has been extensively employed to align large language models with user intent. However, proximal policy optimization (PPO) based RLHF is occasionally unstable requiring significant hyperparameter finetuning, and computationally expensive to maximize the estimated reward during alignment. Recently, direct preference optimization (DPO) is proposed to address those challenges. However, DPO relies on contrastive responses generated from human annotator and alternative LLM, instead of the policy model, limiting the effectiveness of the RLHF. In this paper, we addresses both challenges by systematically combining rejection sampling (RS) and DPO. Our proposed method, RS-DPO, initiates with the development of a supervised fine-tuned policy model (SFT). A varied set of k responses per prompt are sampled directly from the SFT model. RS-DPO identifies pairs of contrastive samples based on their reward distribution. Finally, we apply DPO with the contrastive samples to align the model to human preference. Our experiments indicate that our proposed method effectively fine-tunes LLMs with limited resource environments, leading to improved alignment with user intent. Furthermore, it outperforms existing methods, including RS, PPO, and DPO.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. MetaLint: Easy-to-Hard Generalization for Code Linting

    cs.SE 2025-07 unverdicted novelty 7.0

    MetaLint uses meta-learning to let models generalize from easy synthetic linting data to hard human-curated best practices, yielding large F-score gains on a new PEP-inspired benchmark.

  2. Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion

    cs.AI 2026-05 unverdicted novelty 6.0

    MORA breaks the safety-helpfulness trade-off in LLM alignment by pre-sampling single-reward prompts and rewriting them to expand multi-dimensional reward diversity, yielding 5-12.4% single-preference gains in sequenti...

  3. Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion

    cs.AI 2026-05 unverdicted novelty 6.0

    MORA breaks the safety-helpfulness ceiling in LLMs by pre-sampling single-reward prompts and rewriting them to incorporate multi-dimensional intents, delivering 5-12.4% gains in sequential alignment and 4.6% overall i...