Deep neural networks for improved, impromptu trajectory tracking of quadrotors Q Li, J Qian, Z Zhu, X Bao, MK Helwa, AP Schoellig 2017 IEEE International Conference on Robotics and Automation (ICRA), 5183-5189, 2017 | 110 | 2017 |
How is BERT surprised? Layerwise detection of linguistic anomalies B Li, Z Zhu, G Thomas, Y Xu, F Rudzicz ACL-IJCNLP 1, 4215-4228, 2021 | 33 | 2021 |
Detecting cognitive impairments by agreeing on interpretations of linguistic features Z Zhu, J Novikova, F Rudzicz NAACL 2019, 2018 | 29 | 2018 |
Neural reality of argument structure constructions B Li, Z Zhu, G Thomas, F Rudzicz, Y Xu ACL 2022, 2022 | 28 | 2022 |
An information theoretic view on selecting linguistic probes Z Zhu, F Rudzicz EMNLP 2020, 2020 | 24 | 2020 |
What does the Knowledge Neuron Thesis Have to do with Knowledge? J Niu, A Liu, Z Zhu, G Penn The Twelfth International Conference on Learning Representations, 2024 | 17 | 2024 |
Semi-supervised classification by reaching consensus among modalities Z Zhu, J Novikova, F Rudzicz NeurIPS IRASL Workshop, 2018 | 13 | 2018 |
An unsupervised framework for tracing textual sources of moral change A Ramezani, Z Zhu, F Rudzicz, Y Xu Findings of EMNLP, 2021 | 12 | 2021 |
Examining the rhetorical capacities of neural language models Z Zhu, C Pan, M Abdalla, F Rudzicz EMNLP BlackboxNLP Workshop, 2020 | 12 | 2020 |
Robustness against the channel effect in pathological voice detection YT Hsu, Z Zhu, CT Wang, SH Fang, F Rudzicz, Y Tsao NeurIPS ML4H Workshop, 2018 | 11 | 2018 |
Predicting Fine-Tuning Performance with Probing Z Zhu, S Shahtalebi, F Rudzicz EMNLP, 2022 | 9 | 2022 |
Ccgen: Explainable complementary concept generation in e-commerce J Huang, Y Gao, Z Li, J Yang, Y Song, C Zhang, Z Zhu, H Jiang, ... arXiv preprint arXiv:2305.11480, 2023 | 6 | 2023 |
Deconfounding age effects with fair representation learning when assessing dementia Z Zhu, J Novikova, F Rudzicz arXiv preprint arXiv:1807.07217, 2018 | 6* | 2018 |
Explanation in the Era of Large Language Models Z Zhu, H Chen, X Ye, Q Lyu, C Tan, A Marasović, S Wiegreffe Proceedings of the 2024 Conference of the North American Chapter of the …, 2024 | 4 | 2024 |
On the data requirements of probing Z Zhu, J Wang, B Li, F Rudzicz Findings of ACL, 2022 | 4 | 2022 |
Quantifying the Task-Specific Information in Text-Based Classifications Z Zhu, A Balagopalan, M Ghassemi, F Rudzicz arXiv preprint arXiv:2110.08931, 2021 | 4 | 2021 |
LLM-Generated Black-box Explanations Can Be Adversarially Helpful R Ajwani, SR Javaji, F Rudzicz, Z Zhu NeurIPS 2024 Regulatable ML Workshop, 2024 | 3 | 2024 |
OOD-Probe: A Neural Interpretation of Out-of-Domain Generalization Z Zhu, S Shahtalebi, F Rudzicz ICML 2022: Workshop on Spurious Correlations, Invariance and Stability, 2022 | 3 | 2022 |
How Well Can Knowledge Edit Methods Edit Perplexing Knowledge? H Ge, F Rudzicz, Z Zhu arXiv preprint arXiv:2406.17253, 2024 | 2 | 2024 |
Plug and Play with Prompts: A Prompt Tuning Approach for Controlling Text Generation RD Ajwani, Z Zhu, J Rose, F Rudzicz arXiv preprint arXiv:2404.05143, 2024 | 2 | 2024 |