Steering Llama 2 via Contrastive Activation Addition

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},
}