//
sign in
Post
by @danabra.mov
PostEmbed
by @danabra.mov
Record
by @jimpick.com
Record
by @atsui.org
+ new component
Post
now accepted at ICLR! 🐺🥳🐺 arxiv.org/abs/2506.20666
4mo
Tomer Ullman
NEW on our #DeeperLearning blog People balance being kind vs. being honest — and #LLMs should too. New research shows training choices often favor informativeness over kindness, but prompting can induce sycophancy. Read more: bit.ly/3Wqrtxl
8mo
People’s actions and words are the result of a balance of different goals. The authors use a leading cognitive model of this value trade-off in polite speech to systematically examine […]
bit.ly
Using Cognitive Models to Reveal Value Trade-offs in Language Models - Kempner Institute
Kempner Institute at Harvard University