Pith. sign in

REVIEW 3 cited by

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.10038 v2 pith:AABDAKE2 submitted 2024-02-15 cs.CL cs.AIcs.CVcs.LG

classification cs.CLcs.AIcs.CVcs.LG
keywords modelalignmentcontrastivehumanmethodoptimizationpolicypreference
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Exploring Post-Training Alignment of Small Language Models for Biomedical Data-to-Text Generation: A Case Study of Medication Leaflet

    cs.CL 2026-07 conditional novelty 5.0 of 10

    In medication-leaflet generation, ORPO and GRPO beat SFT and a zero-shot GPT-5 baseline, but GRPO's cross-domain advantage is partly built into its reward functions.

  2. Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation

    cs.LG 2026-02 conditional novelty 4.0 of 10

    A taxonomy-driven survey arguing that reward design is the central mechanism shaping reliable LLM reasoning, with maps of reward paradigms, reward-hacking failure modes, and benchmark pitfalls.

  3. Knowledge-Aware Diverse Reranking for Cross-Source Question Answering

    cs.CL 2025-06 conditional novelty 4.0 of 10

    A knowledge-aware diverse reranking pipeline, combining LLM-based knowledge element extraction with dual-summary reranking, won the SIGIR 2025 LiveRAG competition.

Pith tools