SkMTEB is the first comprehensive text embedding benchmark for Slovak, and vocabulary-trimmed E5 adaptations achieve competitive performance with much smaller models.
arXiv:2502.20936 [cs]
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Entity-based chunk filtering reduces RAG vector index size by 25-36% with retrieval quality near baseline levels.
citing papers explorer
-
SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation
SkMTEB is the first comprehensive text embedding benchmark for Slovak, and vocabulary-trimmed E5 adaptations achieve competitive performance with much smaller models.
-
Reducing Redundancy in Retrieval-Augmented Generation through Chunk Filtering
Entity-based chunk filtering reduces RAG vector index size by 25-36% with retrieval quality near baseline levels.