Jacob Hilton

发表论文 13 篇 · 总被引 40542 次 · h-index 9

代表论文

• Training language models to follow instructions with human feedback (2022 · Neural Information Processing Systems · 被引 23196)
• Training Verifiers to Solve Math Word Problems (2021 · arXiv.org · 被引 10003)
• TruthfulQA: Measuring How Models Mimic Human Falsehoods (2021 · Annual Meeting of the Association for Computational Linguistics · 被引 3734)
• Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022 · arXiv.org · 被引 2586)
• WebGPT: Browser-assisted question-answering with human feedback (2021 · arXiv.org · 被引 2004)
• Scaling Laws for Reward Model Overoptimization (2022 · International Conference on Machine Learning · 被引 1173)