| Sparks of artificial general intelligence: Early experiments with gpt-4 S Bubeck, V Chandrasekaran, R Eldan, J Gehrke, E Horvitz, E Kamar, ... arXiv preprint arXiv:2303.12712, 2023 | 1979 | 2023 |
| Interpretml: A unified framework for machine learning interpretability H Nori, S Jenkins, P Koch, R Caruana arXiv preprint arXiv:1909.09223, 2019 | 525 | 2019 |
| Interpreting interpretability: understanding data scientists' use of interpretability tools for machine learning H Kaur, H Nori, S Jenkins, R Caruana, H Wallach, J Wortman Vaughan Proceedings of the 2020 CHI conference on human factors in computing systems …, 2020 | 490 | 2020 |
| Capabilities of gpt-4 on medical challenge problems H Nori, N King, SM McKinney, D Carignan, E Horvitz arXiv preprint arXiv:2303.13375, 2023 | 431 | 2023 |
| Can generalist foundation models outcompete special-purpose tuning? case study in medicine H Nori, YT Lee, S Zhang, D Carignan, R Edgar, N Fusi, N King, J Larson, ... arXiv preprint arXiv:2311.16452, 2023 | 48 | 2023 |
| An algorithmic framework for differentially private data analysis on trusted processors J Allen, B Ding, J Kulkarni, H Nori, O Ohrimenko, S Yekhanin Advances in Neural Information Processing Systems 32, 2019 | 43 | 2019 |
| Accuracy, Interpretability, and Differential Privacy via Explainable Boosting H Nori, R Caruana, Z Bu, JH Shen, J Kulkarni Proceedings of the 38th International Conference on Machine Learning 139 …, 2021 | 39 | 2021 |
| Intelligible and explainable machine learning: Best practices and practical challenges R Caruana, S Lundberg, MT Ribeiro, H Nori, S Jenkins Proceedings of the 26th ACM SIGKDD international conference on knowledge …, 2020 | 39 | 2020 |
| Comparing population means under local differential privacy: with significance and power B Ding, H Nori, P Li, J Allen Proceedings of the AAAI Conference on Artificial Intelligence 32 (1), 2018 | 36 | 2018 |
| Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv 2023 S Bubeck, V Chandrasekaran, R Eldan, J Gehrke, E Horvitz, E Kamar, ... arXiv preprint arXiv:2303.12712 10, 0 | 35 | |
| Supporting human-ai collaboration in auditing llms with llms C Rastogi, M Tulio Ribeiro, N King, H Nori, S Amershi Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society, 913-926, 2023 | 31 | 2023 |
| Gam changer: Editing generalized additive models with interactive visualization ZJ Wang, A Kale, H Nori, P Stella, M Nunnally, DH Chau, M Vorvoreanu, ... arXiv preprint arXiv:2112.03245, 2021 | 26 | 2021 |
| Interpretability, then what? editing machine learning models to reflect human knowledge and values ZJ Wang, A Kale, H Nori, P Stella, ME Nunnally, DH Chau, M Vorvoreanu, ... Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and …, 2022 | 21 | 2022 |
| Proceedings of the 2020 CHI conference on human factors in computing systems H Kaur, H Nori, S Jenkins, R Caruana, H Wallach, J Wortman Vaughan | 19 | 2020 |
| Remote validation of machine-learning models for data imbalance CL Weider, R Kikin-Gil, HP Nori US Patent 11,537,941, 2022 | 11 | 2022 |
| Differentially private estimation of heterogeneous causal effects F Niu, H Nori, B Quistorff, R Caruana, D Ngwe, A Kannan Conference on Causal Learning and Reasoning, 618-633, 2022 | 10 | 2022 |
| Using explainable boosting machines (ebms) to detect common flaws in data Z Chen, S Tan, H Nori, K Inkpen, Y Lou, R Caruana Joint European Conference on Machine Learning and Knowledge Discovery in …, 2021 | 9 | 2021 |
| Method and system of detecting data imbalance in a dataset used in machine-learning CL Weider, R Kikin-Gil, HP Nori US Patent 11,521,115, 2022 | 8 | 2022 |
| Using interpretable machine learning to predict maternal and fetal outcomes TM Bosschieter, Z Xu, H Lan, BJ Lengerich, H Nori, K Sitcov, V Souter, ... arXiv preprint arXiv:2207.05322, 2022 | 7 | 2022 |
| Remote testing analysis for software optimization based on client-side local differential privacy-based data B Ding, HP Nori, PL Li, JS Allen US Patent 10,902,149, 2021 | 7 | 2021 |
Rich CaruanaMicrosoft ResearchVerified email at microsoft.com
