Nina Rimsky, Nick Gabrieli, Julian Schulz, Meg Tong, Evan Hubinger, Alexander Matt Turner. Steering Llama 2 via Contrastive Activation Addition. In Lun-Wei Ku, Andre Martins, Vivek Srikumar, editors, Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand, August 11-16, 2024. pages 15504-15522, Association for Computational Linguistics, 2024. [doi]
@inproceedings{RimskyGSTHT24, title = {Steering Llama 2 via Contrastive Activation Addition}, author = {Nina Rimsky and Nick Gabrieli and Julian Schulz and Meg Tong and Evan Hubinger and Alexander Matt Turner}, year = {2024}, url = {https://aclanthology.org/2024.acl-long.828}, researchr = {https://researchr.org/publication/RimskyGSTHT24}, cites = {0}, citedby = {0}, pages = {15504-15522}, booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand, August 11-16, 2024}, editor = {Lun-Wei Ku and Andre Martins and Vivek Srikumar}, publisher = {Association for Computational Linguistics}, isbn = {979-8-89176-094-3}, }