A small trained meta-encoder that combines two embedding models improves duplicate-query detection on QQP, but the evaluation is a classification benchmark rather than a real caching workload.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
An Ensemble Embedding Approach for Improving Semantic Caching Performance in LLM-based Systems
A small trained meta-encoder that combines two embedding models improves duplicate-query detection on QQP, but the evaluation is a classification benchmark rather than a real caching workload.