James Evans

Google, Paradigms of Intelligence Team, Knowledge Lab, University of Chicago, Santa Fe Institute, Joint last authors.

Google Research

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Constitutional AI & AI Ethics (1)RLHF & Preference Learning (1)

Frequent co-authors

Junsol Kim (1)Junsol Kim (1)Winnie Street (1)Winnie Street (1)

Papers (1)

Jul 30, 2026

Google Research3w ago·also Institute of Philosophy, Joint last authors., Northwestern, Paradigms of Intelligence Team +2

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

Safety fine-tuning in LLMs not only suppresses self-attribution of consciousness but also inadvertently erases culturally significant beliefs about non-human entities and spirituality.

Junsol Kim, Junsol Kim, Winnie Street +11

Constitutional AI & AI Ethics RLHF & Preference Learning

Search

James Evans

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)