🧑‍🔬 Eric Wallace — all works

26 works · ← Eric Wallace

1. AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated PromptsConference on Empirical Methods in Natural Language Processing (EMNLP)Taylor Shin, Yasaman Razeghi, Robert L. Logan IV, et al.2020 · 1,909 citations
2. Universal Adversarial Triggers for Attacking and Analyzing NLP ↗Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · no summary yetEric Wallace et al.2019 · 989 citations
3. Extracting Training Data from Large Language ModelsarXiv:2012.07805Nicholas Carlini, Florian Tramer, Eric Wallace, et al.2020 · 955 citations
4. Calibrate Before Use: Improving Few-Shot Performance of Language ModelsarXiv:2102.09690Tony Z. Zhao, Eric Wallace, Shi Feng, et al.2021 · 825 citations
5. Evaluating Models' Local Decision Boundaries via Contrast SetsMatt Gardner, Yoav Artzi, Victoria Basmov, et al.Mova's core list · 531 citations
6. Pretrained Transformers Improve Out-of-Distribution RobustnessAnnual Meeting of the Association for Computational Linguistics (ACL)Dan Hendrycks, Xiaoyuan Liu, Eric Wallace, et al.2020 · 452 citations
7. Pathologies of Neural Models Make Interpretations Difficult ↗Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · no summary yetShi Feng et al.2018 · 380 citations
8. Large Language Models Struggle to Learn Long-Tail KnowledgearXiv:2211.08411Nikhil Kandpal, Haikang Deng, Adam Roberts, et al.2022 · 366 citations
9. Do NLP Models Know Numbers? Probing Numeracy in EmbeddingsConference on Empirical Methods in Natural Language Processing (EMNLP)Eric Wallace, Yizhong Wang, Sujian Li, et al.2019 · 352 citations
10. Compositional Questions Do Not Necessitate Multi-hop ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Sewon Min, Eric Wallace, Sameer Singh, et al.2019 · 235 citations
11. Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language ModelsFindings of the Association for Computational LinguisticsRobert Logan IV, Ivana Balazevic, Eric Wallace, et al.2022 · 216 citations
12. Scalable Extraction of Training Data from (Production) Language ModelsarXiv:2311.17035Milad Nasr, Nicholas Carlini, Jonathan Hayase, et al.2023 · 211 citations
13. The False Promise of Imitating Proprietary LLMsarXiv:2305.15717Arnav Gudibande, Eric Wallace, Charlie Snell, et al.2023 · 182 citations
14. AllenNLP Interpret: A Framework for Explaining Predictions of NLP ModelsConference on Empirical Methods in Natural Language Processing (EMNLP)Eric Wallace, Jens Tuyls, Junlin Wang, et al.2019 · 182 citations
15. Trick Me If You Can: Human-in-the-Loop Generation of Adversarial Examples for Question AnsweringTransactions of the Association for Computational Linguistics (TACL)Eric Wallace, Pedro Rodriguez, Shi Feng, et al.2019 · 182 citations
16. Deduplicating Training Data Mitigates Privacy Risks in Language ModelsarXiv:2202.06539Nikhil Kandpal, Eric Wallace, Colin Raffel2022 · 172 citations
17. Concealed Data Poisoning Attacks on NLP Models ↗Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yetEric Wallace et al.2021 · 153 citations
18. Detoxifying Language Models Risks Marginalizing Minority VoicesConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Albert Xu, Eshaan Pathak, Eric Wallace, et al.2021 · 137 citations
19. Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers ↗International Conference on Machine Learning · no summary yetZhuohan Li et al.2020 · 133 citations
20. Deliberative Alignment: Reasoning Enables Safer Language ModelsarXiv:2412.16339Melody Y. Guan, Manas Joglekar, Eric Wallace, et al.2024 · 115 citations
21. Imitation Attacks and Defenses for Black-box Machine Translation Systems ↗Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · no summary yetEric Wallace, Mitchell Stern, Dawn Song2020 · 106 citations
22. Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers ↗arXiv (Cornell University) · no summary yetZhuohan Li et al.2020 · 93 citations
23. The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions ↗arXiv:2404.13208 · no summary yetEric Wallace et al.2024 · 83 citations
24. Interpreting Neural Networks with Nearest Neighbors ↗Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · no summary yetEric Wallace, Shi Feng, Jordan Boyd-Graber2018 · 77 citations
25. Unfamiliar Finetuning Examples Control How Language Models HallucinateConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Katie Kang, Eric Wallace, Claire Tomlin, et al.2025 · 47 citations
26. Automated Crossword Solving ↗Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetEric Wallace et al.2022 · 19 citations

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/eric-wallace/works/