Exposing Attention Glitches with Flip-Flop Language Modeling

Bingbin Liu, Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy, Cyril Zhang. Exposing Attention Glitches with Flip-Flop Language Modeling. 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

Bingbin Liu

This author has not been identified. Look up 'Bingbin Liu' in Google

Jordan T. Ash

This author has not been identified. Look up 'Jordan T. Ash' in Google

Surbhi Goel

This author has not been identified. Look up 'Surbhi Goel' in Google

Akshay Krishnamurthy

This author has not been identified. Look up 'Akshay Krishnamurthy' in Google

Cyril Zhang

This author has not been identified. Look up 'Cyril Zhang' in Google