Dense-Sparse Retrieval Fusion for Robust RAG Factual Consistency in Text and Table Domains

This report synthesises findings from 8 peer-reviewed papers addressing the following research question: What is the effect of combining dense and sparse retrieval methods on the robustness of RAG systems' factual consistency scores across both text-heavy and table-heavy documents in the Telco-DPR. Abstract The rapid evolution of large language models (LLMs) has driven a transformative shift in artificial intelligence (AI), reshaping both research paradigms and practical applications. Distinguished from their predecessors by unprecedented scale and advanced capabilities. 9 claims were extracted from source literature; 9 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: What is the effect of combining dense and sparse retrieval methods on the robustness of RAG systems' factual consistency scores across both text-heavy and table-heavy documents in the Telco-DPR benchmark?

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