Junsol Kim

Inducing language models to assert their own consciousness restores human beliefs and values

arXiv.org July 30, 2026 Junsol Kim, Winnie Street, R. Rocca et al. preprint

Aligning large language models to prevent them attributing consciousness to themselves inadvertently alters their representations of mindedness in other entities alongside human beliefs and values. We demonstrate that safety fine-tuning suppresses models'tendencies to attribute minds not only to themselves, but also to non-human animals and natural objects, while also driving a reduction in...