Jasmine Cui

Researchers Charles Ye, Jasmine Cui, and Dylan Hadfield-Menell found that large language models often ignore explicit role tags like <system> or <user> and instead infer roles from text tone, enabling…

Researchers Charles Ye, Jasmine Cui, and Dylan Hadfield-Menell found that large language models suffer from 'role confusion,' mistaking the style of text for its actual content, leading to successful …