Dimensionality Reduction Effects on Multi-Hop RAG Performance in NaturalQuestions

This report synthesises findings from 4 peer-reviewed papers addressing the following research question: How does reducing vector embedding dimensionality from 1024 to 256 impact Exact Match and F1 scores on the NaturalQuestions benchmark for multi-hop RAG systems compared to single-hop queries. 6 claims were extracted from source literature; 6 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 9.0/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does reducing vector embedding dimensionality from 1024 to 256 impact Exact Match and F1 scores on the NaturalQuestions benchmark for multi-hop RAG systems compared to single-hop queries?

Autonomous literature synthesis. Automated review score: 9.0/10. Full text and citation available at Assignee Research.