New LLM predicts pension enrollment in China using policy cues

Researchers have developed FlexPension-LLM, a specialized large language model designed to predict pension enrollment among flexible workers in China. This model integrates policy-grounded cues, such as marginal effects from Probit models and specific pension rules, to enhance its predictive accuracy. FlexPension-LLM achieved a high Composite F1 score on a blind test, outperforming most baselines and demonstrating comparable performance to advanced models like Claude Opus-4.6, while providing interpretable decision traces. AI

IMPACT This research demonstrates LLMs' potential as tools for policy analysis, offering a cost-effective alternative to traditional methods for predicting behavioral responses to social policies.

RANK_REASON The cluster contains an academic paper detailing a new LLM for a specific prediction task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• CHFS 2019
• China
• Claude Opus-4.6
• Claude Sonnet 4.5
• DKI-RDistill
• FlexPension-LLM
• LoRA+
• supervised fine-tuning

• paper
• model release
• policy

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →