AI RESEARCH
Adaptive Budget Allocation in LLM-Augmented Surveys
arXiv CS.LG
•
ArXi:2604.12497v1 Announce Type: new Large language models (LLMs) can generate survey responses at low cost, but their reliability varies substantially across questions and is unknown before data collection. Deploying LLMs in surveys still requires costly human responses for verification and correction. How should a limited human-labeling budget be allocated across questions in real time? We propose an adaptive allocation algorithm that learns which questions are hardest for the LLM while simultaneously collecting human responses.