| Entity-relation extraction as multi-turn question answering X Li, F Yin, Z Sun, X Li, A Yuan, D Chai, M Zhou, J Li arXiv preprint arXiv:1905.05529, 2019 | 440 | 2019 |
| Glyce: Glyph-vectors for chinese character representations Y Meng, W Wu, F Wang, X Li, P Nie, F Yin, M Li, Q Han, X Sun, J Li Advances in Neural Information Processing Systems 32, 2019 | 232 | 2019 |
| Red teaming language model detectors with language models Z Shi*, Y Wang*, F Yin*, X Chen, KW Chang, CJ Hsieh Transactions of the Association for Computational Linguistic 12, 174-189, 2024 | 49 | 2024 |
| Prompt-driven llm safeguarding via directed representation optimization C Zheng, F Yin, H Zhou, F Meng, J Zhou, KW Chang, M Huang, N Peng arXiv preprint arXiv:2401.18018, 2024 | 46* | 2024 |
| On the Sensitivity and Stability of Model Interpretations in NLP F Yin, Z Shi, CJ Hsieh, KW Chang ACL 2022, 2021 | 37* | 2021 |
| Cleanclip: Mitigating data poisoning attacks in multimodal contrastive learning H Bansal, N Singhi, Y Yang, F Yin, A Grover, KW Chang Proceedings of the IEEE/CVF International Conference on Computer Vision, 112-123, 2023 | 35 | 2023 |
| On the robustness of language encoders against grammatical errors F Yin, Q Long, T Meng, KW Chang arXiv preprint arXiv:2005.05683, 2020 | 33 | 2020 |
| Dynosaur: A dynamic growth paradigm for instruction-tuning data curation D Yin, X Liu, F Yin, M Zhong, H Bansal, J Han, KW Chang arXiv preprint arXiv:2305.14327, 2023 | 31 | 2023 |
| Did you read the instructions? rethinking the effectiveness of task definitions in instruction learning F Yin, J Vig, P Laban, S Joty, C Xiong, CSJ Wu arXiv preprint arXiv:2306.01150, 2023 | 24 | 2023 |
| Active instruction tuning: Improving cross-task generalization by training on prompt sensitive tasks PN Kung, F Yin, D Wu, KW Chang, N Peng arXiv preprint arXiv:2311.00288, 2023 | 14 | 2023 |
| Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension F Yin, J Srinivasa, KW Chang ICML 2024, 2024 | 4 | 2024 |
| Addmu: Detection of far-boundary adversarial examples with data and model uncertainty estimation F Yin, Y Li, CJ Hsieh, KW Chang arXiv preprint arXiv:2210.12396, 2022 | 4 | 2022 |
| Enhancing Large Vision Language Models with Self-Training on Image Comprehension Y Deng, P Lu, F Yin, Z Hu, S Shen, J Zou, KW Chang, W Wang arXiv preprint arXiv:2405.19716, 2024 | 3 | 2024 |
| Efficient shapley values estimation by amortization for text classification C Yang, F Yin, H He, KW Chang, X Ma, B Xiang arXiv preprint arXiv:2305.19998, 2023 | 3 | 2023 |
| Contrastive Instruction Tuning T Yan, F Wang, JY Huang, W Zhou, F Yin, A Galstyan, W Yin, M Chen arXiv preprint arXiv:2402.11138, 2024 | 2 | 2024 |
| Evaluating Human Alignment and Model Faithfulness of LLM Rationale M Fayyaz, F Yin, J Sun, N Peng arXiv preprint arXiv:2407.00219, 2024 | | 2024 |
| Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation D Wu, JC Gu, F Yin, N Peng, KW Chang arXiv preprint arXiv:2406.13692, 2024 | | 2024 |
| Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller M Cai, Y Zhang, S Zhang, F Yin, D Zou, Y Yue, Z Hu arXiv preprint arXiv:2406.02721, 2024 | | 2024 |
Kai-Wei ChangAssociate Professor, UCLAVerified email at kwchang.net
