Re:We read the paper that forced Timnit Gebru out of Google
by visarga on Saturday December 05, 2020 @05:53AM
(#25313519)
You train your LM on web crawl data, but also train a 4chan classifier, then you condition your LM not to generate in 4chan style. GPT-3 got a similar chaperone classifier for offensive speech. It's like knowing swear words but choosing not to use them. You could also condition a general LM to bias and debias its outputs as you like.
[ Parent
| on HN ]
There are no comments on this comment yet.