Asher Zheng
banner
asher-zheng.bsky.social
Asher Zheng
@asher-zheng.bsky.social
PhD @ UT Linguistics
Semantics/Pragmatics/NLP
https://asherz720.github.io/
Prev.@UoEdinburgh @Hanyang
Pinned
Language is often strategic, but LLMs tend to play nice. How strategic are they really? Probing into that is key for future safety alignment.

👉Introducing CoBRA🐍, a framework that assesses strategic language.

Work with my amazing advisors @jessyjli.bsky.social and @David I. Beaver!
Language is often strategic, but LLMs tend to play nice. How strategic are they really? Probing into that is key for future safety alignment.

👉Introducing CoBRA🐍, a framework that assesses strategic language.

Work with my amazing advisors @jessyjli.bsky.social and @David I. Beaver!
June 3, 2025 at 11:56 AM
Reposted by Asher Zheng
Have that eerie feeling of déjà vu when reading model-generated text 👀, but can’t pinpoint the specific words or phrases 👀?

✨We introduce QUDsim, to quantify discourse similarities beyond lexical, syntactic, and content overlap.
April 21, 2025 at 9:29 PM