In-Context Impersonation Reveals Large Language Models' Strengths and Biases
This work addresses the problem of understanding LLMs' adaptability and biases for researchers and practitioners in AI, though it is incremental in building on existing in-context learning methods.
The study explored whether large language models (LLMs) can impersonate different roles, such as social identities or domain experts, in-context to solve tasks, finding that impersonation improved performance in some cases (e.g., bird experts described birds better than car experts) but also revealed biases (e.g., models prompted as men described cars better than those as women).
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. We ask LLMs to assume different personas before solving vision and language tasks. We do this by prefixing the prompt with a persona that is associated either with a social identity or domain expertise. In a multi-armed bandit task, we find that LLMs pretending to be children of different ages recover human-like developmental stages of exploration. In a language-based reasoning task, we find that LLMs impersonating domain experts perform better than LLMs impersonating non-domain experts. Finally, we test whether LLMs' impersonations are complementary to visual information when describing different categories. We find that impersonation can improve performance: an LLM prompted to be a bird expert describes birds better than one prompted to be a car expert. However, impersonation can also uncover LLMs' biases: an LLM prompted to be a man describes cars better than one prompted to be a woman. These findings demonstrate that LLMs are capable of taking on diverse roles and that this in-context impersonation can be used to uncover their hidden strengths and biases.