3 citations · 4 across the 7 of their papers we have counts for
7 papers · 1 filter
How Well Do LLMs Predict Human Behavior? A Measure of their Pretrained Knowledge
Wayne Gao, Sukjin Han, Annie Liang
Large language models (LLMs) are increasingly used to predict human behavior. We propose a measure for evaluating how much knowledge a pretrained LLM brings to such a prediction: i…
Copyright and Competition: Estimating Supply and Demand with Unstructured Data
Sukjin Han, Kyungho Lee
We study the competitive and welfare effects of copyright in creative industries in the face of cost-reducing technologies such as generative artificial intelligence. Creative prod…
Mining Causality: AI-Assisted Search for Instrumental Variables
Sukjin Han
The instrumental variables (IVs) method is a leading empirical strategy for causal inference. Finding IVs is a heuristic and creative process, and justifying its validity -- especi…
Inference for Interval-Identified Parameters Selected from an Estimated Set
Sukjin Han, Adam McCloskey
Interval identification of parameters such as average treatment effects, average partial effects and welfare is particularly common when using observational data and experimental d…
Set-Valued Control Functions
Sukjin Han, Hiroaki Kaido
The control function approach allows the researcher to identify various causal effects of interest. While powerful, it requires a strong invertibility assumption in the selection p…
Testing Information Ordering for Strategic Agents
Sukjin Han, Hiroaki Kaido, Lorenzo Magnolfi
Specifying the information structure in strategic environments is difficult for empirical researchers. We develop a test of information ordering that examines whether the true info…