Qiyu Li

← Portfolio

Research Aug. 2025 – Dec. 2025

LLM-Generated Proxy Features for Tabular Data

Using a language model to manufacture features for text-heavy tabular datasets, then measuring what that buys conventional models.

What I did

  • Built an LLM-based proxy-feature pipeline for text-heavy tabular datasets to improve downstream classification and regression models.
  • Applied the framework to both classification and regression settings on crime and California housing datasets.
  • Designed a modular prompting framework with 7 prompting strategies for reusable, scalable feature generation.
  • Added batch-processing workflows to support larger-scale prompt execution and evaluation.
  • Improved crime classification by up to 0.02 in AUC-ROC and average precision, and improved California housing regression by 10% in R-squared and RMSE.

Built with

  • LLM prompting
  • Classification
  • Regression
  • Batch processing