Wenxuan Wang
Ph.D. Student
ARISE Lab
Department of Computer Science and Engineering
The Chinese University of Hong Kong
Hong Kong SAR, China.
E-mail: wxwang[AT]cse.cuhk.edu.hk
[Curriculum Vitae][Google Scholar]
|
|
Biography
I am a final year Ph.D. student at the Department of Computer Science and Engineering at The Chinese University of Hong Kong (CUHK). I feel lucky to be advised by Prof. Michael R. Lyu . I was a visiting Ph.D. student at UCLA, working with Prof. Nanyun Violet Peng . I also work closely with Dr. Zhaopeng Tu from Tencent AI Lab and Prof. Pinjia He from CUHK(SZ). I received my B.E. degree from the Department of Computer Science and Technology, Huazhong University of Science and Technology (HUST).
Research Interests
The reliability and safety of AI models and software, such as large language models, multi-modal models, code intelligence models, and medical intelligence models.
Selected Publications
Preprint
-
Wenxuan Wang, Juluan Shi, Chaozheng Wang, Cheryl Lee, Youliang Yuan, Jen-tse Huang and Michael R. Lyu.
Learning to Ask: When LLMs Meet Unclear Instruction.
Preprint
-
Wenxuan Wang, Yihang Su, Jingyuan Huan, Jie Liu, Wenting Chen, Yudi Zhang, Cheng-Yi Li, Kao-Jung Chang, Xiaohan Xin, Linlin Shen, and Michael R. Lyu.
Asclepius: A Spectrum Evaluation Benchmark for Medical Multi-Modal Large Language Models.
Preprint
-
Wenxuan Wang, Juluan Shi, Zhaopeng Tu, Youliang Yuan, Jen-tse Huang, Wenxiang Jiao and Michael R. Lyu.
The Earth is Flat? Unveiling Factual Errors in Large Language Models.
Preprint
2024
-
Yuxuan Wan*, Wenxuan Wang*, Wenxiang Jiao, Yiliu Yang, Youliang Yuan, Jen-tse Huang, Pinjia He and Michael R. Lyu.
A ∧ B ⇔ B ∧ A: Triggering Logical Reasoning Failures in Large Language Models.
EMNLP 2024: The 2024 Conference on Empirical Methods in Natural Language Processing.
-
Wenxuan Wang, Haonan Bai, Jen-tse Huang, Jingyuan Huang, Haoyi Qiu, Nanyun Violet Peng, and Michael R. Lyu.
New Job, New Gender? Measuring the Social Bias in Image Generation Models.
ACM MM 2024 (Oral): ACM Multimedia 2024.
-
Wenxuan Wang, Wenxiang Jiao, Jingyuan Huang, Ruyi Dai, Jen-tse Huang, Zhaopeng Tu and Michael R. Lyu.
Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models.
ACL 2024: 62th Annual Meeting of the Association for Computational Linguistics.
-
Wenxuan Wang, Zhaopeng Tu, Chang Chen, Youliang Yuan, Jen-tse Huang, Wenxiang Jiao and Michael R. Lyu.
All Languages Matter: On the Multilingual Safety of Large Language Models.
ACL 2024 Findings: Findings of 62th Annual Meeting of the Association for Computational Linguistics.
-
Wenxuan Wang, Wenxiang Jiao, Shuo Wang, Zhaopeng Tu and Michael R. Lyu.
Understanding and Mitigating the Uncertainty in Zero-Shot Translation.
TASLP 2024: The IEEE/ACM Transactions on Audio, Speech, and Language Processing.
-
Jen-tse Huang, Man Ho Lam, Eric John Li, Shujie Ren, Wenxuan Wang (Corresponding), Wenxiang Jiao, and Michael R. Lyu.
Apathetic or Empathetic? Evaluating LLMs' Emotional Alignments with Humans.
NeurIPS 2024: The Thirty-Eighth Annual Conference on Neural Information Processing Systems.
-
Jen-tse Huang, Wenxiang Jiao, Man Ho Lam, Eric John Li, Wenxuan Wang (Corresponding) and Michael R. Lyu.
On the Reliability of Psychological Scales on Large Language Models.
EMNLP 2024: The 2024 Conference on Empirical Methods in Natural Language Processing.
-
Jen-tse Huang, Wenxuan Wang, Eric John Li, Man Ho Lam, Shujie Ren, Youliang Yuan, Wenxiang Jiao, Zhaopeng Tu, Michael R Lyu.
Who is ChatGPT? Benchmarking LLMs' Psychological Portrayal Using PsychoBench.
ICLR 2024 (Oral): Twelfth International Conference on Learning Representations.
-
Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, Jen-tse Huang, Pinjia He, Shuming Shi, Zhaopeng Tu.
Gpt-4 Is Too Smart To Be Safe: Stealthy Chat With LLMs Via Cipher.
ICLR 2024: Twelfth International Conference on Learning Representations.
-
Kunyu Wang, Xuanran He, Wenxuan Wang, Xiaosen Wang.
Boosting Adversarial Transferability by Block Shuffle and Rotation.
CVPR 2024: IEEE Conference on Computer Vision and Pattern Recognition.
-
Chaozheng Wang, Shuzheng Gao, Cuiyun Gao, Wenxuan Wang, Chun Yong Chong, Shan Gao, Michael R. Lyu.
A Systematic Evaluation of Large Code Models in API Suggestion: When, Which, and How.
ASE 2024: The 39th IEEE/ACM International Conference on Automated Software Engineering.
-
Youliang Yuan, Wenxuan Wang, Qingshuo Guo, Yiming Xiong, Chihao Shen, Pinjia He.
Does ChatGPT Know that It Does Not Know? Evaluating the Black-Box Calibration of ChatGPT.
COLING 2024 (Oral): International Conference on Computational Linguistics.
2023
-
Wenxuan Wang, Jingyuan Huang, Jen-tse Huang, Chang Chen, Pinjia He, Jiazhen Gu and Michael R. Lyu.
A Picture is Worth a Thousand Toxic Words: A Metamorphic Testing Framework for Content Moderation Software.
ASE 2023: The 38th IEEE/ACM International Conference on Automated Software Engineering.
-
Yuxuan Wan*, Wenxuan Wang*, Pinjia He, Jiazhen Gu, Haonan Bai and Michael R. Lyu.
BiasAsker: Measuring the Bias in Conversational AI System.
FSE 2023: The ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering.
-
Wenxuan Wang, Jingyuan Huang, Chang Chen, Jiazhen Gu, Jianping Zhang, Weibin Wu, Pinjia He and Michael R. Lyu.
Validating Multimedia Content Moderation Software via Semantic Fusion.
ISSTA 2023: The 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis.
-
Wenxuan Wang, Jen-tse Huang, Weibin Wu, Jianping Zhang, Yizhan Huang, Shuqing Li, Pinjia He and Michael R. Lyu.
MTTM: Metamorphic Testing for Textual Content Moderation Software.
ICSE 2023: 2023 International Conference on Software Engineering.
-
Yun Peng, Chaozheng Wang, Wenxuan Wang, Cuiyun Gao and Michael R. Lyu.
Generative Type Inference for Python.
ASE 2023 (ACM Distinguished Paper Award): The 38th IEEE/ACM International Conference on Automated Software Engineering.
-
Shuzheng Gao, Xin-cheng Wen, Cuiyun Gao, Wenxuan Wang and Michael R. Lyu.
Constructing Effective In‐Context Demonstration for Code Intelligence Tasks: An Empirical Study.
ASE 2023: The 38th IEEE/ACM International Conference on Automated Software Engineering.
-
Wenxiang Jiao, Jen-tse Huang, Wenxuan Wang, Xing Wang, Shuming Shi and Zhaopeng Tu.
Parrot: Translating During Chat Using Large Language Models.
EMNLP 2023 Findings: The 2023 Conference on Empirical Methods in Natural Language Processing.
-
Jianping Zhang, Jen-tse Huang, Wenxuan Wang, Weibin Wu, Xiaosen Wang, Yuxin Su and Michael R. Lyu.
Improving the Transferability of Adversarial Samples by Path‐Augmented Method.
CVPR 2023: The 2023 IEEE/CVF Computer Vision and Pattern Recognition Conference.
2022
-
Wenxuan Wang, Wenxiang Jiao, Yongchang Hao, Xing Wang, Shuming Shi, Zhaopeng Tu and Michael R. Lyu.
Understanding and Improving Sequence‐to‐Sequence Pretraining for Neural Machine Translation.
ACL 2022: 60th Annual Meeting of the Association for Computational Linguistics.
-
Jianping Zhang, Weibin Wu, Jen-tse Huang, Yizhan Huang, Wenxuan Wang, Yuxin Su and Michael R. Lyu.
Improving Adversarial Transferability via Neuron Attribution‐Based Attacks.
CVPR 2022: The 2022 IEEE/CVF Computer Vision and Pattern Recognition Conference.
2020
-
Wenxuan Wang and Zhaopeng Tu.
Rethinking the Value of Transformer Components.
COLING 2020: Proceedings of The 28th International Conference on Computational Linguistics.
-
Dabiao Ma*, Zhiba Su*, Wenxuan Wang* and Yuhao Lu.
FPETS: Fully Parallel End-to-End Text-to-Speech System..
AAAI 2020 (Oral): Proceedings of The Thirty-Fourth AAAI Conference on Artificial Intelligence.
Experiences
-
Visiting Student: UCLA NLP Group.
07.2023-02.2024
It's my pleasure to work with my host professor, Nanyun Violet Peng, on the Evaluation of Multimodal Large Models.
-
Research Intern: Tencent AI Lab.
07.2019-07.2023
It's my pleasure to work with my mentor, Zhaopeng Tu, on Neural Machine Translation.
-
Research Engineer: Turing Robot.
07.2017-08.2018
Working on Multi-modal Emotion Recognition and Text-to-Speech Synthesis..