Story

arxiv_cs_ai ยท Apr 24, 2026 ยท paper

Source brief

Aligning Dense Retrievers with LLM Utility via DistillationAligning Dense Retrievers with LLM Utility via Distillation

arxiv.orgApr 24, 2026
original source linked

In brief

Dense vector retrieval is the practical backbone of Retrieval- Augmented Generation (RAG), but similarity search can suffer from precision limitations. Conversely, utility-based approaches leveraging LLM re-ranking of...

Continue reading

Read the original at arxiv.org โ†’Open in live feed

Earlier in this thread 1 item