Centralized matching mechanisms outperform free negotiation in stability and efficiency with LLM agents, who also report preferences truthfully more often than humans, though not always in line with strategy-proofness predictions.
Random silicon sampling: Simulating human sub-population opinion using a large language model based on group-level demographic information
7 Pith papers cite this work, alongside 7 external citations. Polarity classification is still indexing.
7
Pith papers citing it
7
external citations · external index
representative citing papers
Value-based personas sampled from real survey distributions, plus a calibration step, reduce LLM prediction error on cross-country surveys especially for underrepresented populations.
AgentSociety is a large-scale LLM agent-based social simulator validated on polarization, UBI, disasters, and sustainability issues with alignment to real experiments.
Fine-tuning LLMs on small pilot survey data balances structural, marginal, and individual fidelity better than prompting or rectification, but fidelity levels vary across subsamples in a COVID-19 misinformation case study.
A PMT-constrained LLM framework with A-TLM configuration outperforms classical imputation methods on RMSE and bias for block-wise missing disaster survey data.
Introduces PAS and FAS task abstractions plus the LLM-S^3 benchmark to evaluate LLMs on generating sociodemographic survey responses across 11 real datasets and multiple models.
Simple supervision improves LLM distributional alignment with diverse population groups on three datasets, with evaluation across multiple models and prompts providing a benchmark.
citing papers explorer
-
Do Matching Mechanisms Work with LLM Agents?
Centralized matching mechanisms outperform free negotiation in stability and efficiency with LLM agents, who also report preferences truthfully more often than humans, though not always in line with strategy-proofness predictions.
-
Improving Cross-Cultural Survey Simulation with Calibrated Value Personas
Value-based personas sampled from real survey distributions, plus a calibration step, reduce LLM prediction error on cross-country surveys especially for underrepresented populations.
-
AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society
AgentSociety is a large-scale LLM agent-based social simulator validated on polarization, UBI, disasters, and sustainability issues with alignment to real experiments.
-
Beyond the Mean: Three-Axis Fidelity for Aligning LLM-Based Survey Simulators from Small Pilot Data
Fine-tuning LLMs on small pilot survey data balances structural, marginal, and individual fidelity better than prompting or rectification, but fidelity levels vary across subsamples in a COVID-19 misinformation case study.
-
Can Large Language Models Revolutionize Survey Research? Experiments with Disaster Preparedness Responses
A PMT-constrained LLM framework with A-TLM configuration outperforms classical imputation methods on RMSE and bias for block-wise missing disaster survey data.
-
Large Language Models as Virtual Survey Respondents: Evaluating Sociodemographic Response Generation
Introduces PAS and FAS task abstractions plus the LLM-S^3 benchmark to evaluate LLMs on generating sociodemographic survey responses across 11 real datasets and multiple models.
-
Improving the Distributional Alignment of LLMs using Supervision
Simple supervision improves LLM distributional alignment with diverse population groups on three datasets, with evaluation across multiple models and prompts providing a benchmark.