Understanding and Mitigating Role Spoofing in LLMs
Despite growing capabilities, LLMs remain susceptible to prompt injections: malicious inputs that can manipulate or hijack models. In particular, it has recently been observed that LLMs can exhibit role confusion (Ye et al., 2026), where models attribute the source of text based on its style instead of its labeled role...
Ezra Edelman, Benjamin L. Edelman, Surbhi Goel et al.
· 0 citations