| ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection T Hartvigsen, S Gabriel, H Palangi, M Sap, D Ray, E Kamar ACL 2022, 2022 | 429 | 2022 |
| Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors T Hartvigsen, S Sankaranarayanan, H Palangi, Y Kim, M Ghassemi Advances in Neural Information Processing Systems 36, 2023 | 124 | 2023 |
| The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations A Balagopalan, H Zhang, K Hamidieh, T Hartvigsen, F Rudzicz, ... FAccT 2022, 2022 | 91 | 2022 |
| Human attention maps for text classification: Do humans and neural networks focus on the same words? C Sen, T Hartvigsen, B Yin, X Kong, ER Rundensteiner ACL 2020, 2020 | 82* | 2020 |
| Adaptive-Halting Policy Network for Early Classification T Hartvigsen, C Sen, X Kong, E Rundensteiner KDD 2019, 2019 | 60 | 2019 |
| Are Language Models Actually Useful for Time Series Forecasting? M Tan, MA Merrill, V Gupta, T Althoff, T Hartvigsen NeurIPS 2024 (Spotlight), 2024 | 34 | 2024 |
| Interpretable unified language checking T Zhang, H Luo, YS Chuang, W Fang, L Gaitskell, T Hartvigsen, X Wu, ... arXiv preprint arXiv:2304.03728, 2023 | 32 | 2023 |
| Units: Building a unified time series model S Gao, T Koker, O Queen, T Hartvigsen, T Tsiligkaridis, M Zitnik NeurIPS 2024, 2024 | 31* | 2024 |
| Learning Saliency Maps to Explain Deep Time Series Classifiers P Parvatharaju, R Doddaiah, T Hartvigsen, E Rundensteiner CIKM 2021, 2021 | 31 | 2021 |
| Demographic bias in misdiagnosis by computational pathology models A Vaidya, RJ Chen, DFK Williamson, AH Song, G Jaume, Y Yang, ... Nature Medicine 30 (4), 1174-1190, 2024 | 27 | 2024 |
| Recurrent Bayesian Classifier Chains for Exact Multi-label Classification W Gerych, T Hartvigsen, L Buquicchio, E Agu, E Rundensteiner NeurIPS 2021, 2021 | 26 | 2021 |
| Early Prediction of MRSA Infections using Electronic Health Records T Hartvigsen, C Sen, S Brownell, E Teeple, X Kong, EA Rundensteiner International Conference on Health Informatics, 156-167, 2018 | 26 | 2018 |
| Recurrent Halting Chain for Early Multi-label Classification T Hartvigsen, C Sen, X Kong, E Rundensteiner KDD 2020, 2020 | 25* | 2020 |
| Recovering the Propensity Score from Biased Positive Unlabeled Data W Gerych, T Hartvigsen, L Buquicchio, E Agu, E Rundensteiner AAAI 2022, 2022 | 22 | 2022 |
| Language Models Still Struggle to Zero-shot Reason about Time Series MA Merrill, M Tan, V Gupta, T Hartvigsen, T Althoff EMNLP 2024 (Findings), 2024 | 18 | 2024 |
| Semi-Supervised Knowledge Amalgamation for Sequence Classification J Thadajarassiri, T Hartvigsen, X Kong, E Rundensteiner AAAI 2021, 2021 | 15* | 2021 |
| Crest-risk prediction for clostridium difficile infection using multimodal data mining C Sen, T Hartvigsen, E Rundensteiner, K Claypool ECML 2017, 2017 | 15 | 2017 |
| Stop&Hop: Early Classification of Irregular Time Series T Hartvigsen, W Gerych, J Thadajarassiri, X Kong, E Rundensteiner CIKM 2022, 2022 | 13* | 2022 |
| PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models D Jain, P Kumar, S Gehman, X Zhou, T Hartvigsen, M Sap COLM 2024, 2024 | 12 | 2024 |
| Encoding time-series explanations through self-supervised model behavior consistency O Queen, T Hartvigsen, T Koker, H He, T Tsiligkaridis, M Zitnik Advances in Neural Information Processing Systems 36, 2023 | 12 | 2023 |
Elke RundensteinerThe William Smith Dean's Professor, Computer Science; Founding Head, Data Science Program; Worcester在 wpi.edu 的电子邮件经过验证
