In-Context Impersonation Reveals Large Language Models' Strengths and Biases
Leonard Salewski, Stephan Alaniz, Isabel Rio-Torto, Eric Schulz, Zeynep Akata
–Neural Information Processing Systems
In everyday conversations, humans can take on different roles and adapt their vocabulary to their chosen roles. We explore whether LLMs can take on, that is impersonate, different roles when they generate text in-context.
Neural Information Processing Systems
Feb-17-2026, 15:43:37 GMT
- Country:
- Asia > Middle East
- Jordan (0.04)
- Europe > Germany
- Baden-Württemberg > Tübingen Region > Tübingen (0.04)
- Asia > Middle East
- Genre:
- Research Report > New Finding (1.00)
- Industry:
- Education (0.47)
- Technology: