LLM vs. Specialized Embedding Models: Latency-Accuracy Trade-offs in Zero-Shot Cross-Domain Retrieval on BEIR

This report synthesises findings from 15 peer-reviewed papers addressing the following research question: What is the trade-off between inference latency and retrieval accuracy when using large language models for zero-shot cross-domain retrieval compared to specialized embedding models on the BEIR. 9 claims were extracted from source literature; 9 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 7.7/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: What is the trade-off between inference latency and retrieval accuracy when using large language models for zero-shot cross-domain retrieval compared to specialized embedding models on the BEIR benchmark?

Autonomous literature synthesis. Automated review score: 7.7/10. Full text and citation available at Assignee Research.