ZHANHUI ZHOU

My research is broadly situated in the field of human-centered NLP, where I focus on developing (1) scalable algorithms that align language models with human values and (2) interactive systems that enhance human experiences by leveraging stronger language models and continuously improving through human interaction. I hold dual bachelor's degrees from UMich and SJTU. Here is my CV.

Selected Publications

Please see Google Scholar for a complete and up-to-date list of publications
Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models
Zhanhui Zhou, Zhixuan Liu, Jie Liu, Zhichen Dong, Chao Yang, Yu Qiao
NeurIPS 2024
PAPER CODE
Emulated Disalignment: Safety Alignment for Large Langugae Models May Backfire!
Zhanhui Zhou, Jie Liu, Zhichen Dong, Jiaheng Liu, Chao Yang, Wanli Ouyang, Yu Qiao
ACL 2024, Outstanding Paper Award (< 1% of all submissions)
PAPER CODE
Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization
Zhanhui Zhou*, Jie Liu*, Chao Yang, Jing Shao, Xiangyu Yue, Wanli Ouyang, Yu Qiao
ACL 2024 Findings
PAPER CODE
INTENT: Interactive Tensor Transformation Synthesis
Zhanhui Zhou*, Man To Tang*, Qiping Pan*, Shangyin Tan, Xinyu Wang, Tianyi Zhang
UIST 2022
PAPER CODE
Inference-Time Language Model Alignment via Integrated Value Guidance
Zhixuan Liu*, Zhanhui Zhou*, Yuanfu Wang, Chao Yang, Yu Qiao
EMNLP 2024 Findings
PAPER 
MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues
Ge Bai, Jie Liu, Xingyuan Bu, Yancheng He, Jiaheng Liu, Zhanhui Zhou, Zhuoran Lin, Wenbo Su, Tiezheng Ge, Bo Zheng, Wanli Ouyang
ACL 2024
PAPER CODE
ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models
Yanan Wu, Jie Liu, Xingyuan Bu, Jiaheng Liu, Zhanhui Zhou, Yuanxing Zhang, Chenchen Zhang, Zhiqi Bai, Haibin Chen, Tiezheng Ge, Wanli Ouyang, Wenbo Su, Bo Zheng
ACL 2024 Findings
PAPER CODE
Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey
Zhichen Dong*, Zhanhui Zhou*, Chao Yang, Jing Shao, Yu Qiao
NAACL 2024
PAPER PAPER LIST