| Rexuie: a recursive method with explicit schema instructor for universal information extraction C Liu, F Zhao, Y Kang, J Zhang, X Zhou, C Sun, K Kuang, F Wu arXiv preprint arXiv:2304.14770, 2023 | 11 | 2023 |
| Goal-Oriented Prompt Attack and Safety Evaluation for LLMs C Liu, F Zhao, L Qing, Y Kang, C Sun, K Kuang, F Wu arXiv e-prints, arXiv: 2309.11830, 2023 | 5 | 2023 |
| Evolving Knowledge Distillation with Large Language Models and Active Learning C Liu, Y Kang, F Zhao, K Kuang, Z Jiang, C Sun, F Wu arXiv preprint arXiv:2403.06414, 2024 | 3 | 2024 |
| A chinese prompt attack dataset for llms with evil content C Liu, F Zhao, L Qing, Y Kang, C Sun, K Kuang, F Wu arXiv preprint arXiv:2309.11830, 2023 | 3 | 2023 |
| Investigating the Robustness of Natural Language Generation from Logical Forms via Counterfactual Samples C Liu, L Gan, K Kuang, F Wu arXiv preprint arXiv:2210.08548, 2022 | 2 | 2022 |
| More Than Catastrophic Forgetting: Integrating General Capabilities For Domain-Specific LLMs C Liu, S Wang, Y Kang, L Qing, F Zhao, C Sun, K Kuang, F Wu arXiv preprint arXiv:2405.17830, 2024 | 1 | 2024 |
| RexUniNLU: Recursive Method with Explicit Schema Instructor for Universal NLU C Liu, S Wang, F Zhao, K Kuang, Y Kang, W Lu, C Sun, F Wu arXiv preprint arXiv:2409.05275, 2024 | | 2024 |
Kun KuangZhejiang University在 zju.edu.cn 的电子邮件经过验证
