arXiv:2410.18451v1 Announce Type: cross
Abstract: In this report, we introduce a collection of methods to enhance reward modeling for LLMs, focusing specifically on data-centric techniques. We propose effective data selection and filtering strategies for curating high-quality open-source preference datasets, culminating in the Skywork-Reward data collection, which contains only 80K preference pairs — significantly smaller than existing datasets. Using this curated dataset, we developed the Skywork-Reward model series — Skywork-Reward-Gemma-27B and Skywork-Reward-Llama-3.1-8B — with the former currently holding the top position on the RewardBench leaderboard. Notably, our techniques and datasets have directly enhanced the performance of many top-ranked models on RewardBench, highlighting the practical impact of our contributions in real-world preference learning applications.
Source link
lol
