WebGPT: Browser-assisted question-answering with human feedback
https://arxiv.org/abs/2112.09332
日本語で読める https://e4exp.hatenablog.com/entry/2022/02/23/193623
OpenAIがGPT-3をfine tuneした
text-based browser
https://openai.com/index/webgpt/
The model is provided with an open-ended question and a summary of the browser state, and must issue commands such as “Search ...”, “Find in page: ...” or “Quote: …”.
論文のFigure 1 (b)
評価
ELI5: Long Form Question Answering
TruthfulQA: Measuring How Models Mimic Human Falsehoods
論文を積ん読