Zeyu (Steven) He 何泽宇

Ph.D. Candidate, Pennsylvania State University

zeyuhe [at] psu [dot] edu

I am on the industry job market for Research Scientist / Applied Scientist roles starting in early 2027. Feel free to reach out!

I am currently a fifth-year Ph.D. candidate in College of Information Sciences and Technology (IST), at Pennsylvania State University working on NLP + HCI areas. I am fortunate to be advised by Dr. Ting-hao (Kenneth) Huang at CrowdAI Lab. Prior to my Ph.D., I obtained my Bachelor's degree in Computer Science & Engineering and Civil Engineering from University of California, Irvine.

NEWS

• Sep 2026 Our new paper, "Experts Rise Where LLMs Disagree: Using Cross-Model Disagreement to Target Expert Effort in LLM Codebook Revision for Large-Scale Annotation", is now available on arXiv.
• July 2026 Thrilled to share that I will join Google's X, the Moonshot Factory as a PhD Resident this Fall!
• June 2026 Our Paper, "PERSONAJUDGE: Simulating Individual Human Preference Judgments with Evaluator-Specific Demonstration Data" based on my internship work at AWS Bedrock is accepted by SIGDIAL 2026.
• May 2026 Our paper "How To Steer Your Multi-Agent System: Human-LLM Collaborative Planning" received the 🏆 Best Artifact Award at CAIS 2026!
• April 2026 Our Paper, "How To Steer Your Multi-Agent System: Human-LLM Collaborative Planning" based on my internship work at Megagon Labs is accepted by CAIS 2026.
• Feb 2026 I gave an invited talk, "What Will Be the Human Role in Data Labeling in This Era of LLMs?", at Cornell University, Department of Information Science.
• August 2025 Thrilled to share that I will be joining Megagon Labs as a Research Scientist Intern this Fall!
• May 2025 Excited to announce that I join AWS Bedrock as an Applied Scientist Intern this Summer!
• April 2025 I passed my Ph.D. Thesis Proposal! I am now a Ph.D. candidate!
• Jan 2025 Our Paper, "Prompting in the Dark: Assessing Human Performance in Prompt Engineering for Data Labeling When Gold Labels Are Absent", is accepted by CHI 2025.
• July 2024 My thesis proposal is accepted by the Doctoral Consortium of HCOMP 2024!
• June 2024 Our Paper, "What Color Scheme is More Effective in Assisting Readers to Locate Information in a Color-Coded Article?", is accepted by VIS 2024.
• Mar 2024 Our Paper, "How Does Conversation Length Impact User’s Satisfaction? A Case Study of Length-Controlled Conversations with LLM-Powered Chatbots", is accepted by CHI LBW 2024.
• Jan 2024 Our Paper, "If in a Crowdsourced Data Annotation Pipeline, a GPT-4", is accepted by CHI 2024.
• May 2023 I passed Qualifying Exam!