Hello! My name is Yangqiaoyu Zhou (I also go by Rosa). I am a Senior Applied Scientist at Microsoft, where I work on synthetic data and evaluation for AI agents in Microsoft Teams: generating synthetic data, measuring its quality, and using it to evaluate agents before deployment.
I received my PhD in Computer Science from the University of Chicago, where I worked with Chenhao Tan in the CHAI lab. During my PhD, I studied how large language models can support scientific discovery by generating hypotheses that explain patterns in data and incorporate insights from existing literature, and how natural language explanations can improve model capabilities such as few-shot learning and robustness to out-of-distribution data.
I am broadly interested in post-training data, LLM and agent evaluation, and AI for science.
Besides research, I like rock climbing, playing the Erhu, and painting.
Publications
- A Single Rewrite Suffices: Empirical Lessons from Production Skill Description Optimization Yangqiaoyu Zhou, Mohammad Alqudah, Kwei-Herng Lai, Aaron Halfaker, Yingqi Xiong, Yaar Harari arXiv, 2026
- Literature Meets Data: A Synergistic Approach to Hypothesis Generation Haokun Liu*, Yangqiaoyu Zhou*, Mingxuan Li*, Chenfei Yuan, Chenhao Tan ACL, 2025 Oral Presentation *Equal contribution
- HypoBench: Towards Systematic and Principled Benchmarking for Hypothesis Generation Haokun Liu, Sicong Huang, Jingyu Hu, Yangqiaoyu Zhou, Chenhao Tan arXiv, 2025
- Hypothesis Generation with Large Language Models Yangqiaoyu Zhou, Haokun Liu, Tejes Srivastava, Hongyuan Mei, Chenhao Tan EMNLP Workshop on NLP for Science, 2024 [Poster] [Code]
- 🔥FLamE: Few Shot Learning From Explanations Yangqiaoyu Zhou, Yiming Zhang, Chenhao Tan ACL, 2023 Oral Presentation [Poster] [Video]
- Learning to Ignore Adversarial Attacks Yiming Zhang, Yangqiaoyu Zhou, Samuel Carton, Chenhao Tan EACL, 2023
- Investigating the Effect of Natural Language Explanations on Out-of-distribution Generalization in Few-shot NLI Yangqiaoyu Zhou and Chenhao Tan EMNLP Workshop on Insights from Negative Results in NLP, 2021 [Code] [Video]
- GraPhyC: Using Consensus to Infer Tumor Evolution Kiya Govek, Camden Sikes, Yangqiaoyu Zhou, Layla Oesper IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2020