Role-Conditioned Refusals: Evaluating Access Control Reasoning in Large Language Models.
Dorde Klisura, Joseph Khoury, Ashish Kundu, Ram Krishnan, Anthony Rios
Browse the full EACL paper archive.
Dorde Klisura, Joseph Khoury, Ashish Kundu, Ram Krishnan, Anthony Rios
Browse the full EACL paper archive.