LabCompass

Ziang Xiao

Computer Science · Purdue University West Lafayette

Early career · publishing since 2017Rising activity

Publications

81

Citations

1,295

Est. group size

Recurring co-author estimate

Active years

10

Publishing since 2017

Research summary
AI-generated

Ziang Xiao studies how people interact with AI systems, particularly large language models (LLMs) and conversational agents, focusing on issues like trust, oversight, personality simulation, privacy, and evaluation methods. This work sits at the intersection of human-computer interaction (HCI) and natural language processing, examining both the design of AI tools (e.g., chatbots, coding assistants, computer-use agents) and how to responsibly test and audit them using human subjects or simulated data.

Human-AI interaction and oversightLarge language model evaluation and auditingConversational AI and chatbot designAI ethics, privacy, and manipulative interface risksPersonality and behavioral simulation with AI

Publication output has grown substantially over the last decade, rising sharply from just a few papers per year before 2022 to around 14-20 per year in 2024-2026.

Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026

Publication cadence
Publications per year over the last 10 years — averaging 12.4/year recently
2017: 1 publication172018: 6 publications182019: 5 publications192020: 4 publications202021: 3 publications212022: 1 publication222023: 10 publications232024: 17 publications242025: 20 publications20252026: 14 publications26
Recent publications
Publishes in
  • arXiv (Cornell University)×28
  • Proceedings of the ACM on Human-Computer Interaction×4
  • Human-computer interaction series×2
  • ACM Transactions on Computer-Human Interaction×1
  • IEEE Access×1
Similar researchers
By research-topic overlap

This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.

Last updated Jul 20, 2026.

Claim or correct this profile