Pith. sign in

REVIEW 2 cited by

Fine-Tuning Language Models with Reward Learning on Policy

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 2403.19279 v1 pith:YOITWZFA submitted 2024-03-28 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords policylearningrewardpreferencedatahumanllmsmodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Reinforcement learning from human feedback (RLHF) has emerged as an effective approach to aligning large language models (LLMs) to human preferences. RLHF contains three steps, i.e., human preference collecting, reward learning, and policy optimization, which are usually performed serially. Despite its popularity, however, (fixed) reward models may suffer from inaccurate off-distribution, since policy optimization continuously shifts LLMs' data distribution. Repeatedly collecting new preference data from the latest LLMs may alleviate this issue, which unfortunately makes the resulting system more complicated and difficult to optimize. In this paper, we propose reward learning on policy (RLP), an unsupervised framework that refines a reward model using policy samples to keep it on-distribution. Specifically, an unsupervised multi-view learning method is introduced to learn robust representations of policy samples. Meanwhile, a synthetic preference generation approach is developed to simulate high-quality preference data with policy outputs. Extensive experiments on three benchmark datasets show that RLP consistently outperforms the state-of-the-art. Our code is available at \url{https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/rlp}.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Non-differentiable Reward Optimization for Diffusion-based Autonomous Motion Planning

    cs.RO 2025-07 conditional novelty 6.0 of 10

    A reinforcement learning fine-tuning method with dynamic reward thresholding lets diffusion motion planners directly optimize non-differentiable safety and goal-reaching metrics, improving collision rate and success r...

  2. Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy

    cs.AI 2025-05 reject novelty 4.0 of 10

    AI copilot preference optimization is organized into a pre-, mid-, and post-interaction taxonomy, with a unified definition of AI copilots.

Pith tools