Demystifying Embedding Spaces using Large Language Models

arXiv:2310.04475v2 Announce Type: replace-cross
Abstract: Embeddings have become a pivotal means to represent complex, multi-faceted information about entities, concepts, and relationships in a condensed and useful format. Nevertheless, they often preclude direct interpretation. While downstream tasks make use of these compressed representations, meaningful interpretation usually requires visualization using dimensionality reduction or specialized machine learning interpretability methods. This paper addresses the challenge of making such embeddings more interpretable and broadly useful, by employing Large Language Models (LLMs) to directly interact with …

abstract arxiv become concepts cs.ai cs.cl cs.lg dimensionality embedding embeddings format information interpretation language language models large language large language models machine pivotal relationships spaces tasks type visualization