Data and Code for Understanding Generative AI Content with Embedding Models

Dataset · Mon Aug 25 04:00:00 EDT 2025

DOI:https://doi.org/10.25584/2587970· OSTI ID:2587970

Vargas, Max ^[1]; Engel, Andrew W ^[1]; Chiang, Tony Y ^[1]; Cannon, Reilly T ^[1]; Sarwate, Anand D ^[2]

---

1. Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
2. Rutgers Univ., Piscataway, NJ (United States)

This repository contains code for the experiments in the paper "Understanding Generative AI Content with Embedding Models". Constructing high-quality features is critical to any quantitative data analysis. While feature engineering was historically addressed by carefully hand-crafting data representations based on domain expertise, deep neural networks (DNNs) now offer a radically different approach. DNNs implicitly engineer features by transforming their input data into hidden feature vectors called embeddings. For embedding vectors produced by foundation models -- which are trained to be useful across many contexts -- we demonstrate that simple and well-studied dimensionality-reduction techniques such as Principal Component Analysis uncover inherent heterogeneity in input data concordant with human-understandable explanations. Of the many applications for this framework, we find empirical evidence that there is intrinsic separability between real samples and those generated by artificial intelligence (AI).

• Research Organization: PNNL (PNNL2)
• Sponsoring Organization: PNNL
• DOE Contract Number: AC05-76RL01830
• OSTI ID: 2587970
• Country of Publication: United States
• Language: English