Working Paper: CEPR ID: DP17923
Authors: Anton Korinek
Abstract: Large language models (LLMs) such as ChatGPT have the potential to revolutionize research in economics and other disciplines. I describe 25 use cases along six domains in which LLMs are starting to become useful as both research assistants and tutors: ideation, writing, background research, data analysis, coding, and mathematical derivations. I provide general instructions and demonstrate specific examples for how to take advantage of each of these, classifying the LLM capabilities from experimental to highly useful. I hypothesize that ongoing advances will improve the performance of LLMs across all of these domains, and that economic researchers who take advantage of LLMs to automate micro tasks will become significantly more productive. Finally, I speculate on the longer-term implications of cognitive automation via LLMs for economic research.
Keywords: Artificial Intelligence; Large Language Models; Cognitive Automation
JEL Codes: A10; B41; J23; O30
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Ongoing advances in LLMs (C51) | Improved performance in various tasks (D29) |
| Improved performance in various tasks (D29) | Increased productivity of economic researchers (O49) |
| Incorporation of LLMs into workflows (Y20) | Increased efficiency in micro tasks (D61) |
| Cognitive automation via LLMs (C45) | Transformation of economic research landscape (O52) |
| Cognitive automation via LLMs (C45) | Displacement of human economists (A11) |