Title: Paradigm Reshaping: AI-Assisted Empirical Replication, Text Analysis, and Model Fine-Tuning in Economics

Speaker: Yang Haisheng, Professor and Doctoral Supervisor, Lingnan College, Sun Yat-sen University.

Abstract: Focusing on "economics research in the intelligent era", this lecture comprehensively demonstrates how artificial intelligence deeply empowers the entire process of basic economic research and empirical analysis. It first explores how to use advanced AI programming environments such as Claude Code to efficiently process complex data and assist in writing Python and Stata scripts, thereby greatly shortening the replication cycle of classic empirical papers. Then, combined with cutting-edge literature, it deeply analyzes how to guide large language models through prompt engineering to accurately extract structured micro data from massive unstructured texts and effectively address the "hallucination" problem of large models. In terms of literature reading and framework construction, it demonstrates on-site how to use dedicated knowledge base tools such as NotebookLM to quickly generate literature reviews and presentation PPT based on a specified PDF literature library without fabrication, helping researchers break through information overload. Finally, it focuses on analyzing the localization fine-tuning practice of large models in the vertical field of economics, systematically introducing the application path of LoRA technology, and exploring how to make open-source basic models deeply learn and capture specific economic laws through instruction fine-tuning, so as to build dedicated measurement and prediction tools with "domain intuition" in economics.

Date & time: 20 May 2026, 12:15 - 13:15

Venue: B321, Zhixin Building, Central Campus, Shandong University