PhD Student @ University of Southern California working in Human-Robot Interaction @ Interaction Lab. BS in CS and MS in NLP @ beautiful UC Santa Cruz.
Can LLMs infer human actions and motives the way humans do?
In our ACL Findings paper led by @ShresthaKaleen and co-authored by Abhinav Gupta, Harish Dukkipati, and Maja Mataric, we examine this question using a validated game theory framework from cognitive science. We find that current LLMs struggle both to recognize statistical patterns in human behavior and to identify humans’ underlying motives.
These findings highlight important limitations in LLMs’ social reasoning capabilities, raising concerns about their ability to accurately simulate human behavior.
Our paper can be found here: https://t.co/hLiCzmi8MR, and feel free to reach out to Kaleen for further questions!
[Blog Post Announcement] The internet is full of “interesting” data: cat videos, think pieces, and highlight reels—but robots often need to learn from mundane data to help us with everyday unexciting tasks. While people aren’t incentivized to share this boring data, we constantly generate it throughout our day (without logging it).
I wrote a blog post for the USC RASC Blog to explore how ~embodied interfaces~ can help us collect the data that users naturally produce to help robots learn about the world:
https://t.co/Fxk4IFSVWl
This blog post is an introduction to what I will talk about at @RSSPioneers! I would love to meet up with anyone who will be attending #RSS2025