# Revisiting RAG Retrievers: An Information Theoretic Benchmark

arXiv: https://arxiv.org/abs/2602.21553 · HTML: https://mlsanity.com/paper/2602.21553/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 28 of its 37 references that are in the map.
- First posted on arXiv 25 Feb 2026.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 28 of 28)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [LightRAG: Simple and Fast Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.05779/) (2024)
- [Benchmarking Large Language Models in Retrieval-Augmented Generation](https://mlsanity.com/paper/2309.01431/) (2023)
- [From RAG to Memory: Non-Parametric Continual Learning for Large Language Models](https://mlsanity.com/paper/2502.14802/) (2025)
- [RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2407.11005/) (2024)
- [HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction](https://mlsanity.com/paper/2408.04948/) (2024)
- [OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain](https://mlsanity.com/paper/2412.13018/) (2024)
- [HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applications](https://mlsanity.com/paper/2409.09046/) (2024)
- [BIRCO: A Benchmark of Information Retrieval Tasks with Complex Objectives](https://mlsanity.com/paper/2402.14151/) (2024)
- [Vendi-RAG: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With LLMs](https://mlsanity.com/paper/2502.11228/) (2025)
- [Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.16415/) (2025)
- [LevelRAG: Enhancing Retrieval-Augmented Generation with Multi-hop Logic Planning over Rewriting Augmented Searchers](https://mlsanity.com/paper/2502.18139/) (2025)
- [ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering](https://mlsanity.com/paper/2506.00232/) (2025)
- [Influence Guided Context Selection for Effective Retrieval-Augmented Generation](https://mlsanity.com/paper/2509.21359/) (2025)
- [WeKnow-RAG: An Adaptive Approach for Retrieval-Augmented Generation Integrating Web Search and Knowledge Graphs](https://mlsanity.com/paper/2408.07611/) (2024)
- [Pointwise Mutual Information as a Performance Gauge for Retrieval-Augmented Generation](https://mlsanity.com/paper/2411.07773/) (2024)
- [HeteRAG: A Heterogeneous Retrieval-augmented Generation Framework with Decoupled Knowledge Representations](https://mlsanity.com/paper/2504.10529/) (2025)
- [Operational Advice for Dense and Sparse Retrievers: HNSW, Flat, or Inverted Indexes?](https://mlsanity.com/paper/2409.06464/) (2024)
- [Prompt-Response Semantic Divergence Metrics for Faithfulness Hallucination and Misalignment Detection in Large Language Models](https://mlsanity.com/paper/2508.10192/) (2025)
- [CReSt: A Comprehensive Benchmark for Retrieval-Augmented Generation with Complex Reasoning over Structured Documents](https://mlsanity.com/paper/2505.17503/) (2025)
- [RePCS: Diagnosing Data Memorization in LLM-Powered Retrieval-Augmented Generation](https://mlsanity.com/paper/2506.15513/) (2025)
- [A Comparative Study of Specialized LLMs as Dense Retrievers](https://mlsanity.com/paper/2507.03958/) (2025)

## Built on by (most cited first, 3 of 3)

- [How Many Tools Should an LLM Agent See? A Chance-Corrected Answer](https://mlsanity.com/paper/2605.24660/) (2026)
- [When Confidence Takes the Wrong Path: Diagnosing Retrieval-State Lock-In in RAG](https://mlsanity.com/paper/2606.22728/) (2026)
- [Quantifying Prior Dominance in RAG Systems](https://mlsanity.com/paper/2606.23695/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) systems rely critically on the retriever module to surface relevant context for large language models. Although numerous retrievers have recently been proposed, each built on different ranking principles such as lexical matching, dense embeddings, or graph citations, there remains a lack of systematic understanding of how these mechanisms differ and overlap. Existing benchmarks primarily compare entire RAG pipelines or introduce new datasets, providing little guidance on selecting or combining retrievers themselves. Those that do compare retrievers directly use a limited set of evaluation tools which fail to capture complementary and overlapping strengths. This work presents MIGRASCOPE, a Mutual Information based RAG Retriever Analysis Scope. We revisit state-of-the-art retrievers and introduce principled metrics grounded in information and statistical estimation theory to quantify retrieval quality, redundancy, synergy, and marginal contribution. We further show that if chosen carefully, an ensemble of retrievers outperforms any single retriever. We leverage the developed tools over major RAG corpora to provide unique insights on contribution levels of the state-of-the-art retrievers. Our findings provide a fresh perspective on the structure of modern retrieval techniques and actionable guidance for designing robust and efficient RAG systems.