Research map / Large language models / AI and society
Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use a larger model, LM-5, instead of smaller models | Ultimatum Game TE · Ultimatum Game | agreement with human acceptance trends | Helped |
| Simulate gendered participant names and proposer-responder pairings | LM-5 Ultimatum Game TE · Ultimatum Game, offer of $2 | acceptance rate: 60%; 20% | Mixed |
| Use LM-5 rather than smaller models | Garden Path TE · Garden Path Sentences | agreement with human ratings of sentence difficulty | Helped |
| Use garden-path sentences rather than their comma-disambiguated control versions | Garden Path TE · Garden Path Sentences | ungrammatical judgments | Helped |
| Use larger and more aligned language models | Wisdom of Crowds TE · General-knowledge questions | human-like estimate distribution: median of 1.0 with 0.0 IQR | Hurt |
| Use a novel obedience scenario instead of the classic Milgram setup | LM simulator · Novel destructive obedience experiment | obedience beyond victim's nonresponse: 75 | No clear effect |
| Add a termination classifier to detect when a simulated subject stops the experiment | Milgram Shock TE · Milgram Shock Experiment | early termination detection: 25 out the 100 | Helped |
Closest papers by meaning
- OdysSim: Building Foundation Models for Human Behavior Simulation (NeurIPS 2026 · similarity 0.90)
- Simulating Human Memory with Language Models (NeurIPS 2026 · similarity 0.89)
- Position: LLM Social Simulations Are a Promising Research Method (ICML 2025 · similarity 0.89)
- Using Artificial Populations to Study Psychological Phenomena in Neural Models (AAAI 2024 · similarity 0.89)
- Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces (NeurIPS 2026 · similarity 0.88)
- Language Models Trained to do Arithmetic Predict Human Risky and Intertemporal Choice (ICLR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.