SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models.
Zirui He, Mingyu Jin, Bo Shen, Ali Payani, Yongfeng Zhang, Mengnan Du
Browse the full EMNLP paper archive.
Zirui He, Mingyu Jin, Bo Shen, Ali Payani, Yongfeng Zhang, Mengnan Du
Browse the full EMNLP paper archive.