| " Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters Y Wan, G Pu, J Sun, A Garimella, KW Chang, N Peng arXiv preprint arXiv:2310.09219, 2023 | 150 | 2023 |
| Theoremqa: A theorem-driven question answering dataset W Chen, M Yin, M Ku, P Lu, Y Wan, X Ma, J Xu, X Wang, T Xia Proceedings of the 2023 Conference on Empirical Methods in Natural Language …, 2023 | 106 | 2023 |
| Improving the Adversarial Robustness of NLP Models by Information Bottleneck C Zhang, X Zhou, Y Wan, X Zheng, KW Chang, CJ Hsieh Findings of the Association for Computational Linguistics: ACL 2022, 3588-3598, 2022 | 33 | 2022 |
| Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems Y Wan, J Zhao, N Peng, KW Chang, A Chadha arXiv preprint arXiv:2310.05280, 2023 | 20 | 2023 |
| Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation Y Wan, A Subramonian, A Ovalle, Z Lin, A Suvarna, C Chance, H Bansal, ... arXiv preprint arXiv:2404.01030, 2024 | 16 | 2024 |
| The Male CEO and the Female Assistant: Probing Gender Biases in Text-To-Image Models Through Paired Stereotype Test Y Wan, KW Chang arXiv preprint arXiv:2402.11089, 2024 | 12 | 2024 |
| White Men Lead, Black Women Help: Uncovering Gender, Racial, and Intersectional Bias in Language Agency Y Wan, KW Chang arXiv preprint arXiv:2404.10508, 2024 | 8 | 2024 |
| PIP: Parse-Instructed Prefix for Syntactically Controlled Paraphrase Generation Y Wan, KH Huang, KW Chang arXiv preprint arXiv:2305.16701, 2023 | 7 | 2023 |
| ABC-KD: Attention-Based-Compression Knowledge Distillation for Deep Learning-Based Noise Suppression Y Wan, Y Zhou, X Peng, KW Chang, Y Lu arXiv preprint arXiv:2305.16665, 2023 | 6 | 2023 |
| Using Item Response Theory to Measure Gender and Racial Bias of a BERT-based Automated English Speech Assessment System A Kwako, Y Wan, J Zhao, KW Chang, L Cai, M Hansen Proceedings of the 17th Workshop on Innovative Use of NLP for Building …, 2022 | 6 | 2022 |
| MACAROON: Training Vision-Language Models To Be Your Engaged Partners S Wu, YR Fung, S Li, Y Wan, KW Chang, H Ji arXiv preprint arXiv:2406.14137, 2024 | 4 | 2024 |
| Does BERT Exacerbate Gender or L1 Biases in Automated English Speaking Assessment? A Kwako, Y Wan, J Zhao, M Hansen, KW Chang, L Cai Proceedings of the 18th Workshop on Innovative Use of NLP for Building …, 2023 | 3 | 2023 |
| Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generation Y Wan, F Wu, W Xu, SH Sengamedu arXiv preprint arXiv:2310.18794, 2023 | 2 | 2023 |
| FACT-OR-FAIR: A Checklist for Behavioral Testing of AI Models on Fairness-Related Queries J Huang, Y Yan, L Liu, Y Wan, W Wang, KW Chang, MR Lyu arXiv preprint arXiv:2502.05849, 2025 | 1 | 2025 |
| The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Intervention Y Wan, D Wu, H Wang, KW Chang arXiv preprint arXiv:2407.00377, 2024 | 1 | 2024 |
| Unlocking the Potential of Text-to-Image Diffusion with PAC-Bayesian Theory EH Jiang, Y Zhang, Z Zhang, Y Wan, A Lizarraga, S Li, YN Wu arXiv preprint arXiv:2411.17472, 2024 | | 2024 |
| MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced With Reliable Evaluations S Zhong, Y Lu, L Shao, B Bhushanam, X Du, L Feng, Y Wan, Y Shi, D Zha, ... | | 2024 |
Kai-Wei ChangAssociate Professor, UCLAכתובת אימייל מאומתת בדומיין kwchang.net