DigiNews

Tech Watch by Johan Denoyer

← Back to articles

"As a Language Model...": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It

Quality: 8/10 Relevance: 9/10

Summary

The paper demonstrates that chat prompts act as a switch that modulates self-referential voice in LLMs, amplifying disclaimers like 'I'm just an AI' when a template is present and reducing them when it is not. It further shows a directional activation in the models that can steer this voice, implying that self-descriptions are shaped by deployment prompts and are not literal facts about the model.

🚀 Service construit par Johan Denoyer