| Universal Adversarial Triggers for Attacking and Analyzing NLP E Wallace, S Feng, N Kandpal, M Gardner, S Singh EMNLP 2019, 2019 | 357 | 2019 |
| Extracting Training Data from Large Language Models N Carlini, F Tramer, E Wallace, M Jagielski, A Herbert-Voss, K Lee, ... USENIX Security 2021, 2020 | 299 | 2020 |
| AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts T Shin, Y Razeghi, RL Logan IV, E Wallace, S Singh EMNLP 2020, 2020 | 292 | 2020 |
| Evaluating Models' Local Decision Boundaries via Contrast Sets M Gardner, Y Artzi, V Basmova, J Berant, B Bogin, S Chen, P Dasigi, ... EMNLP Findings 2020, 2020 | 223 | 2020 |
| Pathologies of Neural Models Make Interpretations Difficult S Feng, E Wallace, II Grissom, M Iyyer, P Rodriguez, J Boyd-Graber EMNLP 2018, 2018 | 208 | 2018 |
| Pretrained Transformers Improve Out-of-Distribution Robustness D Hendrycks, X Liu, E Wallace, A Dziedzic, R Krishnan, D Song ACL 2020, 2020 | 159 | 2020 |
| Do NLP Models Know Numbers? Probing Numeracy in Embeddings E Wallace, Y Wang, S Li, S Singh, M Gardner EMNLP 2019, 2019 | 138 | 2019 |
| Calibrate Before Use: Improving Few-Shot Performance of Language Models TZ Zhao, E Wallace, S Feng, D Klein, S Singh ICML 2021, 2021 | 127 | 2021 |
| Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers Z Li, E Wallace, S Shen, K Lin, K Keutzer, D Klein, JE Gonzalez ICML 2020, 2020 | 122 | 2020 |
| Compositional Questions Do Not Necessitate Multi-hop Reasoning S Min, E Wallace, S Singh, M Gardner, H Hajishirzi, L Zettlemoyer ACL 2019, 2019 | 103 | 2019 |
| Trick Me If You Can: Human-in-the-loop Generation of Adversarial Question Answering Examples E Wallace, P Rodriguez, S Feng, I Yamada, J Boyd-Graber TACL 2019, 2019 | 84* | 2019 |
| AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models E Wallace, J Tuyls, J Wang, S Subramanian, M Gardner, S Singh EMNLP Demo 2019, Best Paper Award, 2019 | 81 | 2019 |
| Imitation Attacks and Defenses for Black-box Machine Translation Systems E Wallace, M Stern, D Song EMNLP 2020, 2020 | 44 | 2020 |
| Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models RL Logan IV, I Balažević, E Wallace, F Petroni, S Singh, S Riedel ACL Findings 2022, 2021 | 37 | 2021 |
| Concealed Data Poisoning Attacks on NLP Models E Wallace, TZ Zhao, S Feng, S Singh NAACL 2021, 2020 | 37* | 2020 |
| Understanding Impacts of High-order Loss Approximations and Features in Deep Learning Interpretation S Singla, E Wallace, S Feng, S Feizi ICML 2019, 2019 | 32 | 2019 |
| Misleading Failures of Partial-Input Baselines S Feng, E Wallace, J Boyd-Graber ACL 2019, 2019 | 30 | 2019 |
| Detoxifying Language Models Risks Marginalizing Minority Voices A Xu, E Pathak, E Wallace, S Gururangan, M Sap, D Klein NAACL 2021, 2021 | 24 | 2021 |
| Gradient-based Analysis of NLP Models is Manipulable J Wang, J Tuyls, E Wallace, S Singh EMNLP Findings 2020, 2020 | 21 | 2020 |
| Deduplicating Training Data Mitigates Privacy Risks in Language Models N Kandpal, E Wallace, C Raffel arXiv preprint arXiv:2202.06539, 2022 | 11 | 2022 |
Sameer SinghAssociate Professor, University of California IrvineПотвърден имейл адрес: uci.edu
