| Multitask prompted training enables zero-shot task generalization V Sanh, A Webson, C Raffel, S Bach, L Sutawika, Z Alyafeai, A Chaffin, ... International Conference on Learning Representations (ICLR), 2022 | 1701 | 2022 |
| Bloom: A 176b-parameter open-access multilingual language model T Le Scao, A Fan, C Akiki, E Pavlick, S Ilić, D Hesslow, R Castagné, ... | 1625 | 2022 |
| Snorkel: Rapid training data creation with weak supervision A Ratner, SH Bach, H Ehrenberg, J Fries, S Wu, C Ré The VLDB Journal 29 (2), 709-730, 2020 | 1346 | 2020 |
| Interpretable decision sets: A joint framework for description and prediction H Lakkaraju, SH Bach, J Leskovec ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2016 | 993 | 2016 |
| Hinge-loss Markov random fields and probabilistic soft logic SH Bach, M Broecheler, B Huang, L Getoor Journal of Machine Learning Research 18 (109), 1-67, 2017 | 522 | 2017 |
| A short introduction to probabilistic soft logic A Kimmig, SH Bach, M Broecheler, B Huang, L Getoor Proceedings of the NIPS Workshop on Probabilistic Programming: Foundations …, 2012 | 327 | 2012 |
| Promptsource: An integrated development environment and repository for natural language prompts SH Bach, V Sanh, ZX Yong, A Webson, C Raffel, NV Nayak, A Sharma, ... arXiv preprint arXiv:2202.01279, 2022 | 319 | 2022 |
| Paired learners for concept drift SH Bach, M Maloof IEEE International Conference on Data Mining (ICDM), 2008 | 221 | 2008 |
| Learning the structure of generative models without labeled data SH Bach, B He, A Ratner, C Ré International Conference on Machine Learning (ICML), 2017 | 194 | 2017 |
| Snorkel DryBell: A case study in deploying weak supervision at industrial scale SH Bach, D Rodriguez, Y Liu, C Luo, H Shao, C Xia, S Sen, A Ratner, ... International Conference on Management of Data (SIGMOD), 2019 | 168 | 2019 |
| Hinge-loss Markov random fields: Convex inference for structured prediction SH Bach, B Huang, B London, L Getoor Uncertainty in Artificial Intelligence (UAI), 2013 | 147 | 2013 |
| Low-resource languages jailbreak gpt-4 ZX Yong, C Menghini, SH Bach arXiv preprint arXiv:2310.02446, 2023 | 140 | 2023 |
| Snorkel: Fast training set generation for information extraction AJ Ratner, SH Bach, HR Ehrenberg, C Ré International Conference on Management of Data (SIGMOD) Demo, 2017 | 102 | 2017 |
| Weakly Supervised Sequence Tagging from Noisy Rules E Safranchik, S Luo, SH Bach AAAI Conference on Artificial Intelligence (AAAI), 2020 | 99 | 2020 |
| Learning to compose soft prompts for compositional zero-shot learning NV Nayak, P Yu, SH Bach arXiv preprint arXiv:2204.03574, 2022 | 68 | 2022 |
| Scaling MPE inference for constrained continuous Markov random fields with consensus optimization SH Bach, M Broecheler, L Getoor, D O'Leary Advances in Neural Information Processing Systems (NIPS), 2012 | 66 | 2012 |
| Fairness via explanation quality: Evaluating disparities in the quality of post hoc explanations J Dai, S Upadhyay, U Aivodji, SH Bach, H Lakkaraju Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society, 203-214, 2022 | 63 | 2022 |
| Language models in the loop: Incorporating prompting into weak supervision R Smith, JA Fries, B Hancock, SH Bach ACM/JMS Journal of Data Science 1 (2), 1-30, 2024 | 48 | 2024 |
| Bigbio: A framework for data-centric biomedical natural language processing J Fries, L Weber, N Seelam, G Altay, D Datta, S Garda, S Kang, R Su, ... Advances in Neural Information Processing Systems 35, 25792-25806, 2022 | 48 | 2022 |
| Does CLIP bind concepts? Probing compositionality in large image models M Lewis, NV Nayak, P Yu, Q Yu, J Merullo, SH Bach, E Pavlick arXiv preprint arXiv:2212.10537, 2022 | 44 | 2022 |
Lise GetoorDistinguished Professor of Computer Science & Engineering, University of California, Santa CruzAdresse e-mail validée de ucsc.edu
