SOURCE-LINKED INTELLIGENCE

Parameter-Efficient Retrievers for Polish and European Languages

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

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 contrastive fine-tuning. It requires no original ground-truth relevance labels, relying exclusively on supervision generated by strong embedding models

Read original source ↗ Open in workspace

recordType

paper

region

Global