🧑‍🔬 Carrie Cai

🏛️ Affiliations

🏢GoogleMountain View · United States2019–2026 · 32 paperscurrent🎓Massachusetts Institute of TechnologyCambridge · United States2013–2017 · 12 papers🔬MIT Computer Science and Artificial Intelligence LaboratoryCambridge · United States2013–2017 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Program Synthesis with Large Language Models (2021 · 1,192 citations)
   The paper asks how far general-purpose large Transformer language models can go at writing short programs in an ordinary language like Python, rather than in a narrow DSL.
2. Social Simulacra: Creating Populated Prototypes for Social Computing Systems (2022 · 310 citations)
   People who design online communities usually test their ideas with a small group of recruited users. Many problems, such as trolling, unclear norms or off-topic content, appear only once a space has many members. The authors propose social simulacra, a prototyping approach that uses GPT-3 to fill a planned community…
3. LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals (2024 · 119 citations)
   Machine-learning models that predict human behavior usually need large amounts of structured data for each specific outcome, so they are hard to reuse for new questions.

All works

5 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

1. Generative Agents: Interactive Simulacra of Human Behavior ↗arXiv:2304.03442 · no summary yetJoon Sung Park et al.2023 · 2,866 citations
2. Program Synthesis with Large Language ModelsarXiv:2108.07732Jacob Austin, Augustus Odena, Maxwell Nye, et al.2021 · 1,192 citations
3. Social Simulacra: Creating Populated Prototypes for Social Computing SystemsarXiv:2208.04024Joon Sung Park, Lindsay Popowski, Carrie J. Cai, et al.2022 · 310 citations
4. LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of IndividualsarXiv:2411.10109Joon Sung Park, Carolyn Q. Zou, Jonne Kamphorst, et al.2024 · 119 citations
5. Simulating Human Behavior Based on Personal Interviews to Power Generative Agent-Based Models ↗no summary yetJoon-Sung Park et al.2024

🤝 Co-authors here

10 co-authors with a page, the most papers together first.

• Joon Sung Park ×2
• Meredith Ringel Morris ×2
• Michael S. Bernstein ×2
• Percy Liang ×2
• Charles Sutton
• David Dohan
• Henryk Michalewski
• Jacob Austin
• Maarten Bosma
• Quoc Viet Le

🔗 Cited by

Papers of our library cite their works 2,162 times (of the 149,439 papers whose bibliographies we read); 614 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/carrie-cai/