LLM Social Simulation is a Promising Research Method

Add to your list(s) Download to your calendar using vCal

• Tiancheng Hu (University of Cambridge)
• Wednesday 17 September 2025, 12:00-13:00
• S3.04, Simon Sainsbury Centre, Cambridge Judge Business School.

If you have a question about this talk, please contact Luning Sun.

The talk is available online. Please get in touch to ask for a Teams invite.

The emergence of large language models as in-silico subjects for social science poses a central question: can they genuinely simulate diverse human behavior, or do they merely produce plausible, homogenized artifacts? This talk demonstrates that LLMs are powerful but imperfect simulators by presenting three core contributions. First, we establish the “Persona Effect,” showing that persona-prompting a 70B model captures 81% of explainable variance in subjective tasks, creating a strong baseline for individual-level simulation. Second, to address data scarcity, we introduce iNews, a large-scale dataset of personalized affective responses to news, enriched with persona information. Finally, we introduce SimBench, the first large-scale benchmark for group-level simulation, which reveals the strengths and critical weaknesses of current models. I conclude by arguing for the specialized datasets and training required to advance the frontier of high-fidelity human simulation.

This talk is part of the Cambridge Psychometrics Centre Seminars series.

This talk is included in these lists:

• Biology
• Cambridge Neuroscience Seminars
• Cambridge Psychometrics Centre Seminars
• Cambridge talks
• Chris Davis' list
• Department of Psychiatry talks stream
• Featured lists
• Life Science
• Life Sciences
• Neuroscience
• Neuroscience Seminars
• Neuroscience Seminars
• Psychology talks and events
• S3.04, Simon Sainsbury Centre, Cambridge Judge Business School
• Stem Cells & Regenerative Medicine
• Yishu's list
• dh539

Note that ex-directory lists are not shown.