Catherine Olsson http://www.semanlink.net/tag/catherine_olsson Documents tagged with Catherine Olsson [2207.05221] Language Models (Mostly) Know What They Know http://www.semanlink.net/doc/2022/09/2207_05221_language_models_m > we show that language models can evaluate whether what they say is true, and predict ahead of time whether they'll be able to answer questions correctly. 2022-09-15T00:11:02Z Anthropic sur Twitter : "a mathematical framework for trying to reverse engineer transformer language models..." http://www.semanlink.net/doc/2021/12/anthropic_sur_twitter_a_math 2021-12-23T00:41:38Z