DOE OSTI · 2481996
Understanding Generative AI Content with Embedding Models
Abstract
The construction of high-quality numerical features is critical to any quantitative data analysis. Feature engineering has been historically addressed by carefully hand-crafting data representations based on domain expertise. This work views the internal representations of modern deep neural networks (DNNs), called embeddings, as an implicit form of traditional feature engineering. For trained DNNs, we show that these embeddings can reveal interpretable, high-level concepts in unstructured sample data. We use these embeddings in natural language and computer vision tasks to uncover both inherent heterogeneity in the underlying data and human-understandable explanations for it. In particular, we find empirical evidence that there is inherent separability between real data and those generated from AI models.
Keep this discovery
Explore connections, maps & timelines
Vargas, Max, Cannon, Reilly T, Engel, Andrew W (ORCID:000000032348483X), Chiang, Tony Y, Sarwate, Anand D. 2024-11-18. Understanding Generative AI Content with Embedding Models. https://doi.org/10.25584/2481996. https://engineeringpapers.com/record/osti%3A2481996/understanding-generative-ai-content-with-embedding-models
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Engineering Papers by Indiciae: BibTeX · RIS.