ICLR Poster Demystifying Embedding Spaces using Large Language Models

iclr.cc · 222 words · saved by 1 readers

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 embeddings -- transforming abstract vectors into understandable narratives. By injecting embeddings into LLMs, we enable querying and exploration of complex embedding data. We demonstrate our approach on a variety of diverse tasks, including: enhancing concept activation vectors (CAVs), communicating novel embedded entities, and decoding user preferences in recommender systems. Our work coupl

ICLR Poster Demystifying Embedding Spaces using Large Language Models ICLR 2024 CSP Test --> Poster Demystifying Embedding Spaces using Large Language Models Guy Tennenholtz ⋅ Yinlam Chow ⋅ ChihWei Hsu ⋅ Jihwan Jeong ⋅ Lior Shani ⋅ Azamat Tulepbergenov ⋅ Deepak Ramachandran ⋅ Martin Mladenov ⋅ Craig Boutilier 2024 Poster [ OpenReview ] 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

ICLR Poster Demystifying Embedding Spaces using Large Language Models

related reading