4.3k citations · 5.2k across the 11 of their papers we have counts for
Showing 2021 · cs.CLShow all
2 papers · 2 filters
cs.CL2021★ 33 cited
WebGPT: Browser-assisted question-answering with human feedback
Reiichiro Nakano, Jacob Hilton, Suchir Balaji +15
We fine-tune GPT-3 to answer long-form questions using a text-based web-browsing environment, which allows the model to search and navigate the web. By setting up the task so that…
cs.CL2021★ 121 cited
TruthfulQA: Measuring How Models Mimic Human Falsehoods
Stephanie Lin, Jacob Hilton, Owain Evans
We propose a benchmark to measure whether a language model is truthful in generating answers to questions. The benchmark comprises 817 questions that span 38 categories, including…