mlsanityData to 7 Oct 2026

COS-Mix: Cosine Similarity and Distance Fusion for Improved Information Retrieval

arXiv 2406.00638 ↗First posted 2 Jun 2024cs.IRcited by 4

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

This study proposes a novel hybrid retrieval strategy for Retrieval-Augmented Generation (RAG) that integrates cosine similarity and cosine distance measures to improve retrieval performance, particularly for sparse data. The traditional cosine similarity measure is widely used to capture the similarity between vectors in high-dimensional spaces. However, it has been shown that this measure can yield arbitrary results in certain scenarios. To address this limitation, we incorporate cosine distance measures to provide a complementary perspective by quantifying the dissimilarity between vectors. Our approach is experimented on proprietary data, unlike recent publications that have used open-source datasets. The proposed method demonstrates enhanced retrieval performance and provides a more comprehensive understanding of the semantic relationships between documents or items. This hybrid strategy offers a promising solution for efficiently and accurately retrieving relevant information in knowledge-intensive applications, leveraging techniques such as BM25 (sparse) retrieval , vector (Dense) retrieval, and cosine distance based retrieval to facilitate efficient information retrieval.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 15 of its 22 references that are in the map. First posted on arXiv 2 Jun 2024.

Builds on

15 of 22 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Corrective Retrieval Augmented Generation29 Jan

Other references · 14

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  4. 2019Language Models as Knowledge Bases?cited by 1,922
  5. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,324
  6. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  7. 2020Fact or Fiction: Verifying Scientific Claimscited by 546
  8. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
  9. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
  10. 2021QuALITY: Question Answering with Long Input Texts, Yes!cited by 204
  11. 2024Is Cosine-Similarity of Embeddings Really About Similarity?cited by 89
  12. 2023Information Retrieval: Recent Advances and Beyondcited by 49
2 more
  1. 2024Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam Generationcited by 25
  2. 2023Keyword Augmented Retrieval: Novel framework for Information Retrieval integrated with speech interfacecited by 11

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 1.

4 papers.

  1. 2024Evaluating the Efficacy of Open-Source LLMs in Enterprise-Specific RAG Systems: A Comparative Study of Performance and Scalabilitycited by 15
  2. 2024Introducing a new hyper-parameter for RAG: Context Window Utilizationcited by 8
  3. 2024A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoningcited by 8
  4. 2025KnowsLM: A framework for evaluation of small language models for knowledge augmentation and humanised conversationscited by 6

Similar, not cited

Close in wording, no citation either way

  1. 2024CoFE-RAG: A Comprehensive Full-chain Evaluation Framework for Retrieval-Augmented Generation with Enhanced Data Diversity
  2. 2026Cross-Attention Calibrated Deduplication for Retrieval-Augmented Generation System
  3. 2025HF-RAG: Hierarchical Fusion-based RAG with Multiple Sources and Rankers
  4. 2024Beyond Benchmarks: Evaluating Embedding Model Similarity for Retrieval Augmented Generation Systems
  5. 2025Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid Search
  6. 2025REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark
  7. 2024ARAGOG: Advanced RAG Output Grading
  8. 2025DAT: Dynamic Alpha Tuning for Hybrid Retrieval in Retrieval-Augmented Generation