| On the Opportunities and Risks of Foundation Models R Bommasani, DA Hudson, E Adeli, R Altman, S Arora, S von Arx, ... whitepaper, 2021 | 2767 | 2021 |
| How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings K Ethayarajh EMNLP, 2019 | 849 | 2019 |
| Utility is in the Eye of the User: A Critique of NLP Leaderboards K Ethayarajh, D Jurafsky EMNLP, 2020 | 143 | 2020 |
| Understanding Undesirable Word Embedding Associations K Ethayarajh, D Duvenaud, G Hirst ACL, 2019 | 139 | 2019 |
| Understanding Dataset Difficulty with -Usable Information K Ethayarajh, Y Choi, S Swayamdipta ICML, 2022 | 133* | 2022 |
| Unsupervised Random Walk Sentence Embeddings: A Strong but Simple Baseline K Ethayarajh ACL - Repl4NLP, 2018 | 111 | 2018 |
| Towards Understanding Linear Word Analogies K Ethayarajh, D Duvenaud, G Hirst ACL, 2019 | 109 | 2019 |
| Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking Z Ma*, K Ethayarajh*, T Thrush*, S Jain, L Wu, R Jia, C Potts, A Williams, ... NeurIPS, 2021 | 49 | 2021 |
| Conditional probing: measuring usable information beyond a baseline J Hewitt, K Ethayarajh, P Liang, CD Manning EMNLP, 2021 | 39 | 2021 |
| Attention Flows are Shapley Value Explanations K Ethayarajh, D Jurafsky ACL, 2021 | 33 | 2021 |
| KTO: Model Alignment as Prospect Theoretic Optimization K Ethayarajh, W Xu, N Muennighoff, D Jurafsky, D Kiela arXiv preprint arXiv:2402.01306, 2024 | 24* | 2024 |
| The Authenticity Gap in Human Evaluation K Ethayarajh, D Jurafsky EMNLP, 2022 | 22* | 2022 |
| Anchor points: Benchmarking models with much fewer examples R Vivek, K Ethayarajh, D Yang, D Kiela arXiv preprint arXiv:2309.08638, 2023 | 4 | 2023 |
Dan JurafskyProfessor of Linguistics and Computer Science, Stanford UniversityVerified email at stanford.edu
