A method using predicted rectification difficulty for optimal human sample allocation in LLM-augmented surveys captures 61-79% of theoretical efficiency gains and reduces MSE by 11% on two datasets without pilot data.
Valid sur- vey simulations with limited human data: The roles of prompting, fine-tuning, and rectification
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
An adaptive budget allocation algorithm for LLM-augmented surveys learns question-level LLM reliability on the fly from human labels and reduces labeling waste from 10-12% to 2-6% compared to uniform allocation.
Narriva generates behavior-grounded text personas from survey data that achieve up to 87% accuracy in predicting privacy decisions, improve 6-17 points over baselines, cut tokens by 80-95%, and reproduce aggregate distributions across different studies.
GEMS formulates close-ended human-behavior simulation as link prediction on a heterogeneous graph and matches or exceeds LLM performance with three orders of magnitude fewer parameters across three datasets and three evaluation settings.
Introduces a 1.2-million-character narrative dataset from 92 residents, benchmarks 18 LLMs on fidelity with life-history profiles, and presents curriculum-LoRA as a low-cost personalization method that matches high-fidelity baselines at 10x lower token cost.
citing papers explorer
-
Rectification Difficulty and Optimal Sample Allocation in LLM-Augmented Surveys
A method using predicted rectification difficulty for optimal human sample allocation in LLM-augmented surveys captures 61-79% of theoretical efficiency gains and reduces MSE by 11% on two datasets without pilot data.
-
Adaptive Budget Allocation in LLM-Augmented Surveys
An adaptive budget allocation algorithm for LLM-augmented surveys learns question-level LLM reliability on the fly from human labels and reduces labeling waste from 10-12% to 2-6% compared to uniform allocation.
-
Text-Based Personas for Simulating User Privacy Decisions
Narriva generates behavior-grounded text personas from survey data that achieve up to 87% accuracy in predicting privacy decisions, improve 6-17 points over baselines, cut tokens by 80-95%, and reproduce aggregate distributions across different studies.
-
Graph-Based Alternatives to LLMs for Human Simulation
GEMS formulates close-ended human-behavior simulation as link prediction on a heterogeneous graph and matches or exceeds LLM performance with three orders of magnitude fewer parameters across three datasets and three evaluation settings.
-
Benchmarking LLMs for Community Governance Simulation with Life-history Narratives
Introduces a 1.2-million-character narrative dataset from 92 residents, benchmarks 18 LLMs on fidelity with life-history profiles, and presents curriculum-LoRA as a low-cost personalization method that matches high-fidelity baselines at 10x lower token cost.