Parameter-Efficient Retrievers for Polish and European Languages

Excerpt

arXiv:2609.12913v1 Announce Type: new Abstract: Dense retrieval systems increasingly rely on multi-billion-parameter language models, whose memory and computational requirements make large-scale indexing, frequent corpus updates, and low-latency serving costly. We present a three-stage training pipeline for developing compact and efficient retrievers that remain competitive with substantially larger models. The pipeline combines cross-lingual alignment, relational knowledge distillation, and con