On the Exploitability of Instruction Tuning

Manli Shu, Jiongxiao Wang, Chen Zhu 0001, Jonas Geiping, Chaowei Xiao, Tom Goldstein. On the Exploitability of Instruction Tuning. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, Sergey Levine, editors, Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023. 2023. [doi]

Authors

Manli Shu

This author has not been identified. Look up 'Manli Shu' in Google

Jiongxiao Wang

This author has not been identified. Look up 'Jiongxiao Wang' in Google

Chen Zhu 0001

This author has not been identified. Look up 'Chen Zhu 0001' in Google

Jonas Geiping

This author has not been identified. Look up 'Jonas Geiping' in Google

Chaowei Xiao

This author has not been identified. Look up 'Chaowei Xiao' in Google

Tom Goldstein

This author has not been identified. Look up 'Tom Goldstein' in Google