Preprint
Aug 2026
The Embedder's Dilemma: LLMs Are Better, but at What Cost?
These results support a division of labour: use embedding models for similarity, classification, and clustering, and reserve LLMs for reasoning-intensive retrieval, and reserve LLMs for reasoning-intensive retrieval.
Adnan El Assadi, Niklas Muennighoff, Jinhyuk Lee
· 1 citation