mlsanityData to 7 Oct 2026

An Analysis of Fusion Functions for Hybrid Retrieval

arXiv 2210.11934 ↗First posted 21 Oct 2022cs.IRcited by 49

Not on the map. Why?

Cited by 24 in Retrieval-augmented generation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We study hybrid search in text retrieval where lexical and semantic search are fused together with the intuition that the two are complementary in how they model relevance. In particular, we examine fusion by a convex combination (CC) of lexical and semantic scores, as well as the Reciprocal Rank Fusion (RRF) method, and identify their advantages and potential pitfalls. Contrary to existing studies, we find RRF to be sensitive to its parameters; that the learning of a CC fusion is generally agnostic to the choice of score normalization; that CC outperforms RRF in in-domain and out-of-domain settings; and finally, that CC is sample efficient, requiring only a small set of training examples to tune its only parameter to a target domain.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Oct 2022.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 7; 2025: 15; 2026: 26.

49 papers.

Sort:

By area:

  1. 2024RAG-Fusion: a New Take on Retrieval-Augmented Generationcited by 42
  2. 2026Skill Retrieval Augmentation for Agentic AIcited by 41
  3. 2024UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systemscited by 38
  4. 2024Customized Retrieval Augmented Generation and Benchmarking for EDA Tool Documentation QAcited by 28
  5. 2024AutoRAG: Automated Framework for optimization of Retrieval Augmented Generation Pipelinecited by 26
  6. 2025Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End Systemcited by 22
  7. 2025Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimizationcited by 10
  8. 2023DAPR: A Benchmark on Document-Aware Passage Retrievalcited by 9
  9. 2025DAT: Dynamic Alpha Tuning for Hybrid Retrieval in Retrieval-Augmented Generationcited by 7
  10. 2024HiQA: A Hierarchical Contextual Augmentation RAG for Multi-Documents QAcited by 5
  11. 2025Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysiscited by 5
  12. 2025IL-PCSR: Legal Corpus for Prior Case and Statute Retrievalcited by 5
37 more
  1. 2026SmartSearch: How Ranking Beats Structure for Conversational Memory Retrievalcited by 5
  2. 2025MedPlan: A Two-Stage RAG-Based System for Personalized Medical Plan Generationcited by 4
  3. 2025Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid Searchcited by 4
  4. 2025StatEval: A Comprehensive Benchmark for Large Language Models in Statisticscited by 4
  5. 2025RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasetscited by 4
  6. 2026SkillSight: Calibrating Generic Content Bias for Skill Retrievalcited by 4
  7. 2025Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformerscited by 3
  8. 2025Test-time Corpus Feedback: From Retrieval to RAGcited by 3
  9. 2024TeleOracle: Fine-Tuned Retrieval-Augmented Generation with Long-Context Support for Networkcited by 2
  10. 2026Developing and evaluating a chatbot to support maternal health carecited by 2
  11. 2026AgentIR: A Workload-Adaptive Cascade Retrieval Substrate for Long-Term Conversational Memorycited by 2
  12. 2024Know When to Fuse: Investigating Non-English Hybrid Retrieval in the Legal Domaincited by 1
  13. 2025Content-based 3D Image Retrieval and a ColBERT-inspired Re-ranking for Tumor Flagging and Stagingcited by 1
  14. 2025KG-CQR: Leveraging Structured Relation Representations in Knowledge Graphs for Contextual Query Retrievalcited by 1
  15. 2026A Reference Architecture for Agentic Hybrid Retrieval in Dataset Searchcited by 1
  16. 2026Conjecture and Inquiry: Quantifying Software Performance Requirements via Interactive Retrieval-Augmented Preference Elicitationcited by 1
  17. 2026LLM-Oriented Information Retrieval: A Denoising-First Perspectivecited by 1
  18. 2026Bringing Agentic Search to Earth Observation Data Discoverycited by 1
  19. 2025All-in-one Graph-based Indexing for Hybrid Search on GPUscited by 0
  20. 2025Intelligent Scientific Literature Explorer using Machine Learning (ISLE)cited by 0
  21. 2026PathoScribe: Transforming Pathology Data into a Living Library with a Unified LLM-Driven Framework for Semantic Retrieval and Clinical Integrationcited by 0
  22. 2026The Virtuous Cycle: AI-Powered Vector Search and Vector Search-Augmented AIcited by 0
  23. 2026ContextClaim: A Context-Driven Paradigm for Verifiable Claim Detectioncited by 0
  24. 2026CogRAG: Tackling Heterogeneous Cognitive Demands in RAG via Stratified Retrieval and Reasoningcited by 0
  25. 2026RAGe: A Retrieval-Augmented Generation Evaluation Frameworkcited by 0
  26. 2026Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answeringcited by 0
  27. 2026Building AI That Works: ESnet's Pragmatic Approach to AI-Driven Operational Excellencecited by 0
  28. 2026A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facilitycited by 0
  29. 2026SciClaimSeekers at CheckThat! 2026: Retrieving Scientific Sources for Social Media Claims with LLM Rerankingcited by 0
  30. 2026Polaris: Learning to Generate Table Descriptions from Retrieval Feedbackcited by 0
  31. 2026Learning to Fuse LLMs with Ontology Rankers for Rare-Disease Diagnosiscited by 0
  32. 2026CHSR-RRF: A curriculum-gated hybrid retrieval framework with reciprocal rank fusion and leakage-aware benchmarking for educational RAGcited by 0
  33. 2026Quanta: A Self-Contained Python Library for Hybrid Retrieval over Quantised Embeddings, Lexical Indexes, and Knowledge Graphscited by 0
  34. 2026Retail Product Search: A Practical Approach at Targetcited by 0
  35. 2026Page-Aware Retrieval-Augmented Generation for EvalLLM 2026: A Five-Variant Study on French PDFscited by 0
  36. 2026PILLAR: Private Inverted-Index Lexical Lookup for Augmented Retrievalcited by 0
  37. 2026MemFit: Efficient Long-Term Agentic Memorycited by 0