Login
Roast topics
Find topics
Find it!
From:
www.lesswrong.com
(Uncensored)
subscribe
Connecting the Dots: LLMs can Infer & Verbalize Latent Structure from Training Data — LessWrong
https://www.lesswrong.com/posts/5SKRHQEFr8wYQHYkx/connecting-the-dots-llms-can-infer-and-verbalize-latent
links
backlinks
Roast topics
Find topics
Roast it!
TL;DR: We published a new paper on out-of-context reasoning in LLMs. We show that LLMs can infer latent information from training data and use this i…
