Yunze (Lorenzo) Xiao

Human–AI interaction · Multi-agent social simulation · Human-centered evaluation

Portrait of Yunze Xiao

I am pursuing an MS in Language Technology at Carnegie Mellon University’s Language Technology Institute, advised by Prof. Mona Diab. I received my BS in Computer Science from Carnegie Mellon University Qatar in May 2025, with a minor in Computational Ethics, working with Prof. Houda Bouamor and Prof. Kemal Oflazer.

I study how AI systems represent, interact with, and simulate people, from individual behavior to collective social dynamics. My work spans anthropomorphism and human-centered evaluation; persona and multi-agent social simulation; and the evidential foundations of AI welfare claims. Looking ahead, I am interested in scalable oversight and trustworthy multi-agent systems, with a focus on understanding and shaping their societal impact.

lyxiao@cmu.edu · CV (PDF) · All publications · GitHub · Teaching & mentoring

News

Jul. 2026Our ACL 2026 papers include Sentipolis, TartanMaroon, The Confidence Dichotomy, and student difficulty estimation.
May 2026I presented Persona Collapse: Measuring Diversity Failures in LLM-Simulated Populations at the STAMINA-WG Research Talk Series.
Apr 26, 2026New blog post & interactive microsite — The Chameleon’s Limit summarizes our preprint on persona collapse in LLMs (explore the microsite).

All news

Selected publications

All publications & preprints

* Equal contribution.

  1. The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Models [W4]

    High persona fidelity can coexist with a homogeneous simulated population: convincing individuals do not guarantee population diversity.

    Yunze Xiao*, Vivienne J. Zhang*, Chenghao Yang, Ningshan Ma, Weihao Xuan, and Jen-tse Huang.

    2026. arXiv:2604.24698.

    Paper Interactive project Research post Code

  2. Sentipolis: Emotion-Aware Agents for Social Simulations [P2]

    Persistent emotion–memory coupling improves emotional continuity in the evaluated simulations; gains in believability depend on the model.

    Chiyuan Fu*, Lyuhao Chen*, Yunze Xiao*, Weihao Xuan, Carlos Busso, and Mona Diab.

    2026. Findings of ACL 2026.

    Paper

  3. TartanMaroon: Multi-Agent Academic Advising with Iterative Negotiation and Transparent Collaboration [P4]

    Iterative proposal–critique negotiation improves constrained degree planning, with greater benefits on complex tasks than on simple factual queries.

    Peidi Dong, Houda Bouamor, Yunze Xiao, and Devi G Kurup.

    2026. ACL 2026, System Demonstrations.

    Paper Code Demo Video

  4. Position: AI Welfare Is Bullshit [P5]

    We argue that AI welfare claims need independent validation beyond steerable behavioral indicators, and that governance should prioritize verifiable harms.

    Yunze Xiao*, Gordon Dai*, Shahan Ali Memon*, Jen-tse Huang, Maarten Sap, and Mona T. Diab.

    2026. ICML 2026, Position Paper Track.

    Paper PDF

  5. Hire Your Anthropologist! Rethinking Culture Benchmarks Through an Anthropological Lens [P7]

    An audit of 20 cultural benchmarks identifies six recurring methodological pitfalls in how cultural knowledge and behavior are evaluated.

    Mai Alkhamissi*, Yunze Xiao*, Badr AlKhamissi, and Mona Diab.

    2026. Findings of EACL 2026.

    Paper

  6. Humanizing Machines: Rethinking LLM Anthropomorphism Through a Multi-Level Framework of Design [P11]

    We propose evaluating anthropomorphic cues against user goals and context, treating human-like design as something to assess rather than simply maximize.

    Yunze Xiao*, Lynnette Hui Xian Ng*, Jiarui Liu, and Mona Diab.

    2025. EMNLP 2025. Oral.

    Paper

Research projects & interactive explanations

  • The Chameleon's Limit — Do distinct persona profiles produce behaviorally diverse populations?
  • Sentipolis — How do persistent emotions shape agent interactions over time?
  • TartanMaroon — When does academic advising need coordination among specialized agents?

Try the persona fidelity and diversity illustration

Contact

lyxiao@cmu.edu · GHC 5418, Carnegie Mellon University

4902 Forbes Ave · Pittsburgh, PA 15213

Schedule a conversationView my calendar

Times shown in Eastern Time (Pittsburgh). You can also email me.