Nakano, 2021 — WebGPT: Browser-Assisted Question-Answering with Human Feedback

DOI: <a href="https://doi.org/10.48550/arXiv.2112.09332" target="_blank" rel="noopener noreferrer">https://doi.org/10.48550/arXiv.2112.09332
URL: <a href="https://arxiv.org/abs/2112.09332" target="_blank" rel="noopener noreferrer">https://arxiv.org/abs/2112.09332

Covers preference-learning or reward-modeling methods used in modern alignment pipelines.

Publication links

Covers preference-learning or reward-modeling methods used in modern alignment pipelines.