"As a Language Model...": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It
- View PDF HTML (experimental) Abstract:Large Language Models (LLMs) tend to add disclaimers like "I'm just an AI" when asked about something related to themselves.
- The self-reports from such responses are used in debates about AI safety or self-knowledge of the models, yet what drives them is not well understood.
- Are the models telling us about themselves or rather how they are deployed?
Unverified
- View PDF HTML (experimental) Abstract:Large Language Models (LLMs) tend to add disclaimers like "I'm just an AI" when asked about something related to themselves.
- The self-reports from such responses are used in debates about AI safety or self-knowledge of the models, yet what drives them is not well understood.
- Are the models telling us about themselves or rather how they are deployed?
Sources: Arxiv