WIRED Asks A New Brown CS Research Group About Multilingual Large Language Models
- Posted by Jesse Polhemus
- on June 5, 2023
Three doctoral students at Brown University's Department of Computer Science (Brown CS) have formed a new research group, and last week, WIRED asked them about the problem of having ChatGPT and its peers be far less capable when faced with non-English languages. Jessica Forde (advised by Brown CS faculty member Michael Littman), Ruochen Zhang (advised by Brown CS faculty member Carsten Eickhoff), and Yong Zheng-Xin (advised by Brown CS faculty member Stephen Bach) have made it their goal to build natural language processing (NLP) technology for Southeast Asian languages.
"English has been so cemented," says Jessica, "because people have been saying (and studying), can this perform like a lawyer in English or a doctor in English? Can this produce a comedy in English? But they aren't saying the same about other languages."
The WIRED article is available here.
A recent paper ("Prompting Multilingual Large Language Models to Generate Code-Mixed
Texts: The Case of South East Asian Languages") by the researchers and their collaborators is available here.
For more information, click the link that follows to contact Brown CS Communications Manager Jesse C. Polhemus.
