I’m a research scientist at Google Deepmind. My research focuses on natural language processing and machine learning, with a particular emphasis on the post-training of large language models. I am especially interested in instruction tuning, preference modeling, and reinforcement learning from human feedback. I earned my Ph.D. from the University of Southern California under the mentorship of Prof. Muhao Chen. Prior to that, I obtained my Bachelor’s degree in Computer Science and Applied Mathematics from HKUST in 2014.
Email: A [at] B, where A=wenxuan.zhou.usc and B is gmail.com
Preprints
-
Wenxuan Zhou, Shujian Zhang, Lingxiao Zhao, Tao Meng. T-REG: Preference Optimization with Token-Level Reward Regularization. Arxiv 2024. [paper]
-
James Y. Huang, Wenxuan Zhou, Fei Wang, Fred Morstatter, Sheng Zhang, Hoifung Poon, Muhao Chen. Offset Unlearning for Large Language Models. Arxiv 2024. [paper]
-
Tong Liu, Xiao Yu, Wenxuan Zhou, Jindong Gu, Volker Tresp. FocalPO: Enhancing Preference Optimizing by Focusing on Correct Preference Rankings. Arxiv 2025. [paper]
Publication
[Organized by Area]
[Full List by Year]
2025
-
Fei Wang, Xingyu Fu, James Y. Huang, Zekun Li, Qin Liu, Xiaogeng Liu, Mingyu Derek Ma, Nan Xu, Wenxuan Zhou, Kai Zhang, Tianyi Lorena Yan, Wenjie Jacky Mo, Hsiang-Hui Liu, Pan Lu, Chunyuan Li, Chaowei Xiao, Kai-Wei Chang, Dan Roth, Sheng Zhang, Hoifung Poon, Muhao Chen. MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding. ICLR 2025. [paper]
-
Tong Wu, Shujian Zhang, Kaiqiang Song, Silei Xu, Sanqiang Zhao, Ravi Agrawal, Sathish Reddy Indurthi, Chong Xiang, Prateek Mittal, Wenxuan Zhou. Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy. ICLR 2025. [paper]
2024
-
Wenxuan Zhou, Ravi Agrawal, Shujian Zhang, Sathish Reddy Indurthi, Sanqiang Zhao, Kaiqiang Song, Silei Xu, Chenguang Zhu. WPO: Enhancing RLHF with Weighted Preference Optimization. EMNLP 2024. [paper] [code] [model]
-
Fei Wang, Wenxuan Zhou, James Y. Huang, Nan Xu, Sheng Zhang, Hoifung Poon, Muhao Chen. mDPO: Conditional Preference Optimization for Multimodal Large Language Models. EMNLP 2024. [paper] [code]
-
Sathish Reddy Indurthi, Wenxuan Zhou, Shamil Chollampatt, Ravi Agrawal, Kaiqiang Song, Lingxiao Zhao, Chenguang Zhu. Improving Multilingual Instruction Finetuning via Linguistically Natural and Diverse Datasets. EMNLP-Findings 2024. [paper]
-
Wenxuan Zhou*, Sheng Zhang*, Yu Gu, Muhao Chen, Hoifung Poon. UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition. ICLR 2024. [paper] [project page] [model]
-
Tianqing Fang, Zhaowei Wang, Wenxuan Zhou, Hongming Zhang, Yangqiu Song, Muhao Chen. Getting Sick After Seeing a Doctor? Diagnosing and Mitigating Knowledge Conflicts in Event Temporal Reasoning. NAACL-Findings 2024. [paper]
-
Tianqing Fang, Wenxuan Zhou, Fangyu Liu, Hongming Zhang, Yangqiu Song, Muhao Chen. On-the-fly Denoising for Data Augmentation in Natural Language Understanding. EACL-Findings 2024. [paper]
-
Tianyi Yan, Fei Wang, James Y. Huang, Wenxuan Zhou, Fan Yin, Aram Galstyan, Wenpeng Yin, Muhao Chen. Contrastive Instruction Tuning. ACL-Findings 2024. [paper]
2023
-
Wenxuan Zhou, Sheng Zhang, Hoifung Poon, Muhao Chen. Context-faithful Prompting for Large Language Models. EMNLP-Findings 2023. [paper] [code]
-
Fei Wang, Wenjie Mo, Yiwei Wang, Wenxuan Zhou, Muhao Chen. A Causal View of Entity Bias in (Large) Language Models. EMNLP-Findings 2023. [paper]
-
Zekun Li, Wenxuan Zhou, Yao-Yi Chiang, Muhao Chen. GeoLM: Empowering Language Models for Geospatially Grounded Language Understanding. EMNLP 2023.
-
Wenxuan Zhou, Sheng Zhang, Tristan Naumann, Muhao Chen, Hoifung Poon. Continual Contrastive Finetuning Improves Low-Resource Relation Extraction. ACL 2023. [paper] [slides]
-
Keming Lu, I-Hung Hsu, Wenxuan Zhou, Mingyu Derek Ma, Muhao Chen. Multi-hop Evidence Retrieval for Cross-document Relation Extraction. ACL-Findings 2023. [paper] [code]
-
Fei Wang, James Y. Huang, Tianyi Yan, Wenxuan Zhou, Muhao Chen. Robust Natural Language Understanding with Residual Attention Debiasing. ACL-Findings, 2023. [paper] [code]
-
Xiaoocong Yang, James Y. Huang, Wenxuan Zhou, Muhao Chen. Parameter-Efficient Tuning with Special Token Adaptation. EACL 2023. [paper] [code]
-
Wenxuan Zhou. Robust and Generalizable Knowledge Acquisition from Text. Ph.D. thesis. [pdf]
2022
-
Wenxuan Zhou, Fangyu Liu, Huan Zhang, Muhao Chen. Sharpness-Aware Minimization with Dynamic Reweighting. EMNLP-Findings 2022. [paper]
-
Keming Lu, I-Hung Hsu, Wenxuan Zhou, Mingyu Derek Ma, Muhao Chen. Summarization as Indirect Supervision for Relation Extraction. EMNLP-Findings 2022. [paper] [code]
-
Wenxuan Zhou, Muhao Chen. An Improved Baseline for Sentence-level Relation Extraction. AACL-IJCNLP 2022. [paper] [code] [slides]
-
Wenxuan Zhou, Qiang Ning, Heba Elfardy, Kevin Small, Muhao Chen. Answer Consolidation: Formulation and Benchmarking. NAACL 2022. [paper] [code] [slides]
-
Yiwei Wang, Muhao Chen, Wenxuan Zhou, Yujun Cai, Yuxuan Liang, Dayiheng Liu, Baosong Yang, Juncheng Liu, Bryan Hooi. Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis. NAACL 2022. [paper] [code]
-
Yiwei Wang, Muhao Chen, Wenxuan Zhou, Yujun Cai, Yuxuan Liang, Bryan Hooi. GraphCache: Message Passing as Caching for Sentence-Level Relation Extraction. NAACL-Findings 2022. [paper]
-
Wenxuan Zhou*, Fangyu Liu*, Ivan Vulić, Nigel Collier, Muhao Chen. Prix-LM: Pretraining for Multilingual Knowledge Base Construction. ACL 2022. [paper] [code] [slides] [model]
2021
-
Wenxuan Zhou, Fangyu Liu, Muhao Chen. Contrastive Out-of-Distribution Detection for Pretrained Transformers. EMNLP 2021. [paper] [code] [slides]
-
Wenxuan Zhou and Muhao Chen. Learning from Noisy Labels for Entity-Centric Information Extraction. EMNLP 2021. [paper] [code] [slides]
-
Wenxuan Zhou, Kevin Huang, Tengyu Ma, Jing Huang. Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling. AAAI 2021. [paper] [code] [slides]
-
Wenxuan Zhou, Bill Yuchen Lin, Xiang Ren. IsoBN: Fine-Tuning BERT with Isotropic Batch Normalization. AAAI 2021. [paper] [code]
2020
-
Wenxuan Zhou, Hongtao Lin, Bill Yuchen Lin, Ziqi Wang, Junyi Du, Leonardo Neves, Xiang Ren. NERO: A Neural Rule Grounding Framework for Label-Efficient Relation Extraction (Honorable Mention Paper). WWW 2020. [paper] [code] [slides]
-
Ziqi Wang, Yujia Qin, Wenxuan Zhou, Jun Yan, Qinyuan Ye, Leonardo Neves, Zhiyuan Liu, Xiang Ren. Learning from Explanations with Neural Execution Tree. ICLR 2020. [paper] [code]
2019
- Ziqian Zheng, Wenxuan Zhou, Xin Liu, Yangqiu Song. A Variational Approach to Weakly Supervised Document-Level Multi-Aspect Sentiment Classification. NAACL-HLT 2019. [paper] [code]
RLHF
-
Wenxuan Zhou, Ravi Agrawal, Shujian Zhang, Sathish Reddy Indurthi, Sanqiang Zhao, Kaiqiang Song, Silei Xu, Chenguang Zhu. WPO: Enhancing RLHF with Weighted Preference Optimization. EMNLP 2024. [paper] [code] [model]
-
Fei Wang, Wenxuan Zhou, James Y. Huang, Nan Xu, Sheng Zhang, Hoifung Poon, Muhao Chen. mDPO: Conditional Preference Optimization for Multimodal Large Language Models. EMNLP 2024. [paper] [code]
LM Safety and Faithfulness
-
Tong Wu, Shujian Zhang, Kaiqiang Song, Silei Xu, Sanqiang Zhao, Ravi Agrawal, Sathish Reddy Indurthi, Chong Xiang, Prateek Mittal, Wenxuan Zhou. Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy. ICLR 2025. [paper]
-
Wenxuan Zhou, Sheng Zhang, Hoifung Poon, Muhao Chen. Context-faithful Prompting for Large Language Models. EMNLP-Findings 2023. [paper] [code]
-
Wenxuan Zhou, Fangyu Liu, Muhao Chen. Contrastive Out-of-Distribution Detection for Pretrained Transformers. EMNLP 2021. [paper] [code] [slides]
-
Wenxuan Zhou*, Sheng Zhang*, Yu Gu, Muhao Chen, Hoifung Poon. UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition. ICLR 2024. [paper] [project page] [model]
-
Wenxuan Zhou and Muhao Chen. Learning from Noisy Labels for Entity-Centric Information Extraction. EMNLP 2021. [paper] [code] [slides]
-
Wenxuan Zhou, Kevin Huang, Tengyu Ma, Jing Huang. Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling. AAAI 2021. [paper] [code] [slides]
-
Wenxuan Zhou, Hongtao Lin, Bill Yuchen Lin, Ziqi Wang, Junyi Du, Leonardo Neves, Xiang Ren. NERO: A Neural Rule Grounding Framework for Label-Efficient Relation Extraction (Honorable Mention Paper). WWW 2020. [paper] [code] [slides]
Service
-
Journal Reviewer: IEEE Transactions on Neural Networks and Learning Systems
, Neural Computing and Applications, Journal of Artificial Intelligence Research
, Nature Machine Intelligence, Neural Networks
-
Area chair: ARR 2024/2025
-
Reviewer: AAAI 2022-2024, ACL 2020-2023, EMNLP 2019-2023, NeurIPS 2024, ICLR 2025, ICML 2025