When Roleplaying, Do Models Believe What They Say?
📰 ArXiv cs.AI
arXiv:2606.11502v1 Announce Type: cross Abstract: Language models can state that "the Earth orbits the Sun" and, when role-playing Aristotle, assert the opposite. Recent work argues that persona adoption is fundamental to how language models operate, with models constantly selecting the most appropriate persona for a given context. Does such role-playing merely change the model's outputs, or does it also affect what the model internally represents as truthful? We study this question with linear
Full Article
Title: When Roleplaying, Do Models Believe What They Say?
Abstract:
arXiv:2606.11502v1 Announce Type: cross Abstract: Language models can state that "the Earth orbits the Sun" and, when role-playing Aristotle, assert the opposite. Recent work argues that persona adoption is fundamental to how language models operate, with models constantly selecting the most appropriate persona for a given context. Does such role-playing merely change the model's outputs, or does it also affect what the model internally represents as truthful? We study this question with linear
Abstract:
arXiv:2606.11502v1 Announce Type: cross Abstract: Language models can state that "the Earth orbits the Sun" and, when role-playing Aristotle, assert the opposite. Recent work argues that persona adoption is fundamental to how language models operate, with models constantly selecting the most appropriate persona for a given context. Does such role-playing merely change the model's outputs, or does it also affect what the model internally represents as truthful? We study this question with linear
DeepCamp AI