Gerald Shen — accepted AI-conference papers

2025

HelpSteer2-Preference: Complementing Ratings with Preferences

Zhilin Wang, Alexander Bukharin, Olivier Delalleau, Daniel Egert, Gerald Shen, Jiaqi Zeng +2

ICLR 2025poster

Reward models are critical for aligning models to follow instructions, and are typically trained following one of two popular paradigms: Bradley-Terry style or Regression style. However, there is a lack of evidence that either approach is better than the other, when adequately matched for data. This…

Cited by 32 Source ↗PDF ↗Scholar ↗

2024

HelpSteer 2: Open-source dataset for training top-performing reward models

Zhilin Wang, Yi Dong, Olivier Delalleau, Jiaqi Zeng, Gerald Shen, Daniel Egert +3

NeurIPS 2024poster

High-quality preference datasets are essential for training reward models that can effectively guide large language models (LLMs) in generating high-quality responses aligned with human preferences. As LLMs become stronger and better aligned, permissively licensed preference datasets, such as Open A…

Cited by 85 Source ↗PDF ↗code ↗Scholar ↗