HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages

TL;DR

HelpSteer3-Preference is a large, open, human-annotated dataset across multiple tasks and languages, significantly improving reward model performance for training instruction-following language models.

Contribution

We introduce a high-quality, diverse, open preference dataset that enhances reward model training and aligns policy models with RLHF across various domains.

Findings

Reward models trained on HelpSteer3-Preference outperform previous models by ~10%.

The dataset covers STEM, coding, and multilingual tasks.

Models trained with this data achieve top benchmark scores.

Abstract

Preference datasets are essential for training general-domain, instruction-following language models with Reinforcement Learning from Human Feedback (RLHF). Each subsequent data release raises expectations for future data collection, meaning there is a constant need to advance the quality and diversity of openly available preference data. To address this need, we introduce HelpSteer3-Preference, a permissively licensed (CC-BY-4.0), high-quality, human-annotated preference dataset comprising of over 40,000 samples. These samples span diverse real-world applications of large language models (LLMs), including tasks relating to STEM, coding and multilingual scenarios. Using HelpSteer3-Preference, we train Reward Models (RMs) that achieve top performance on RM-Bench (82.4%) and JudgeBench (73.7%). This represents a substantial improvement (~10% absolute) over the previously best-reported results from existing RMs. We demonstrate HelpSteer3-Preference can also be applied to train Generative RMs and how policy models can be aligned with RLHF using our RMs. Dataset (CC-BY-4.0): https://huggingface.co/datasets/nvidia/HelpSteer3#preference Models (NVIDIA Open Model): https://huggingface.co/collections/nvidia/reward-models-68377c5955575f71fcc7a2a3