ZEST shows that a small synthetic corpus generated by GPT-4o from five examples can stand in for the real target corpus in a frozen context-aware embedding model, losing under 0.5% retrieval accuracy on MTEB.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Zero-Shot Contextual Embeddings via Offline Synthetic Corpus Generation
ZEST shows that a small synthetic corpus generated by GPT-4o from five examples can stand in for the real target corpus in a frozen context-aware embedding model, losing under 0.5% retrieval accuracy on MTEB.