Asher Zheng (@asher_zheng00) 's Twitter Profile
Asher Zheng

@asher_zheng00

PhD @UT_Linguistics. Semantics, Pragmatics, Computational Linguistics and #NLProc. All opinions are mine.🇨🇳

ID: 1565712912991207424

linkhttps://asherz720.github.io/ calendar_today02-09-2022 14:47:28

4 Tweet

32 Followers

162 Following

Asher Zheng (@asher_zheng00) 's Twitter Profile Photo
Asher Zheng
@asher_zheng00

2 months ago

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 Jessy Li and David 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 <a href="/jessyjli/">Jessy Li</a> and <a href="/David_Beaver/">David Beaver</a>! 🧵👇