@_jasonwei : Nice paper by Tu Vu on factuality in LLMs: arxiv.org/abs/23150.03214, enjoyed contributing in a minor role to it while I was at Google. The main takeaway for me is that most factuality benchmarks for LLMs don't really take into account the fact that many types of knowledge • TwiCopy

Jason Wei

@_jasonwei

+ Follow

ai researcher @openai

ID: 1319101874532978690

linkhttp://jasonwei.net/thoughts calendar_today22-10-2020 02:22:58

1,1K Tweet

82,82K Takipçi

586 Takip Edilen

Jason Wei

@_jasonwei

2 years ago

Nice paper by Tu Vu on factuality in LLMs: arxiv.org/abs/2310.03214, enjoyed contributing in a minor role to it while I was at Google. The main takeaway for me is that most factuality benchmarks for LLMs don't really take into account the fact that many types of knowledge

thumb_up_off_alt115

chat_bubble_outline3

repeat15

shareShare