Mini-Batch K-Means followed by greedy set-cover within each bucket guarantees every sample lands with a representative that is at least α-similar and attribute-identical, reducing LLM inference cost ~50× at 38M-customer scale.
Title resolution pending
1 Pith paper cite this work, alongside 20 external citations. Polarity classification is still indexing.
1
Pith paper citing it
20
external citations · OpenAlex
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient Clustering with Provable Guardrails for LLM Inference at Scale
Mini-Batch K-Means followed by greedy set-cover within each bucket guarantees every sample lands with a representative that is at least α-similar and attribute-identical, reducing LLM inference cost ~50× at 38M-customer scale.