 Causal Analysis of Syntactic Agreement Neurons in Multilingual Language
ModelsConference on Computational Natural Language Learning (CoNLL), 2022 |
 A Causal Framework to Quantify the Robustness of Mathematical Reasoning
with Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Revision Transformers: Instructing Language Models to Change their
ValuesEuropean Conference on Artificial Intelligence (ECAI), 2022 |
 Language Generation Models Can Cause Harm: So What Can We Do About It?
An Actionable SurveyConference of the European Chapter of the Association for Computational Linguistics (EACL), 2022 |
 Mass-Editing Memory in a TransformerInternational Conference on Learning Representations (ICLR), 2022 |
 |
 Extremely Simple Activation Shaping for Out-of-Distribution DetectionInternational Conference on Learning Representations (ICLR), 2022 |
 The Alignment Problem from a Deep Learning PerspectiveInternational Conference on Learning Representations (ICLR), 2022 |
 Memory-Based Model Editing at ScaleInternational Conference on Machine Learning (ICML), 2022 |
