Sanghee J. Kim
@Sanghee__Kim
Postdoctoral Teaching Fellow @UChicago, working on language processing and discourse comprehension
New study on LMs and discourse sensitivity! We evaluate 25 LMs on their ability to prioritize discourse-relevant info, and find that (1) smaller & dialogue-trained models align closer to human patterns, while (2) larger/instruction models overuse structural or discourse cues.

Excited to see our Centaur project out in @Nature. TL;DR: Centaur is a computational model that predicts and simulates human behavior for any experiment described in natural language.
1/ Today in Science, we train a neural net from scratch through the eyes and ears of one child. The model learns to map words to visual referents, showing how grounded language learning from just one child's perspective is possible with today's AI tools. science.org/doi/10.1126/sc…