4 papers
Observational Equivalence of LLM and Human Annotation
Kentaro Nakamura, Jing Ling Tan, George Yean
In this paper, we show that LLM and human coding are observationally equivalent in terms of annotation quality: recent LLMs agree with expert coders at rates comparable to those ob…
Causal Inference with Video Features as Treatments
Kentaro Nakamura, Adam Breuer, Michael H. Crespin +2
We develop the first statistical methodology for causal inference with video features as treatments. Video is the most engaging content modality on the internet. A central causal q…
GenAI Powered Dynamic Causal Inference with Unstructured Data
Kentaro Nakamura, Kosuke Imai
A growing number of scholars seek to estimate causal effects of unstructured data such as text, images, and video. However, existing methods typically treat each object as a single…
Surrogate Representation Inference for Text and Image Annotations
Kentaro Nakamura
As researchers increasingly rely on machine learning models and LLMs to annotate unstructured data, such as texts or images, various approaches have been proposed to correct bias i…