Multi-Attribute Steering of Language Models via Targeted Intervention.
Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal
Browse the full ACL paper archive.
Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal
Browse the full ACL paper archive.