mlsanityData to 7 Oct 2026

How Does Knowledge Selection Help Retrieval Augmented Generation?

arXiv 2410.13258 ↗First posted 17 Oct 2024cs.CLcited by 3

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

Abstract (arXiv)

Retrieval-augmented generation (RAG) is a powerful method for enhancing natural language generation by integrating external knowledge into a model's output. While prior work has demonstrated the importance of improving knowledge retrieval for boosting generation quality, the role of knowledge selection, a.k.a. reranking or filtering, remains less clear. This paper empirically analyzes how knowledge selection influences downstream generation performance in RAG systems. By simulating different retrieval and selection conditions through a controlled mixture of gold and distractor knowledge, we assess the impact of these factors on generation outcomes. Our findings indicate that the downstream generator model's capability, as well as the complexity of the task and dataset, significantly influence the impact of knowledge selection on the overall RAG system performance. In typical scenarios, improving the knowledge recall score is key to enhancing generation outcomes, with the knowledge selector providing limited benefit when a strong generator model is used on clear, well-defined tasks. For weaker generator models or more ambiguous tasks and datasets, the knowledge F1 score becomes a critical factor, and the knowledge selector plays a more prominent role in improving overall performance.

Key facts. Cited by 3 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 24 of its 31 references that are in the map. First posted on arXiv 17 Oct 2024.

Builds on

24 of 31 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG14 Oct
  2. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG8 Oct
  3. 2024RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems25 Jun
  4. 2024The Power of Noise: Redefining Retrieval for RAG Systems26 Jan
  5. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec

Other references · 19

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  8. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  9. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  10. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  11. 2020Sequential Latent Knowledge Selection for Knowledge-Grounded Dialoguecited by 82
  12. 2018Towards Exploiting Background Knowledge for Building Conversation Systemscited by 57
7 more
  1. 2024Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?cited by 53
  2. 2021Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialogcited by 33
  3. 2023Generative Knowledge Selection for Knowledge-Grounded Dialoguescited by 15
  4. 2022Enhanced Knowledge Selection for Grounded Dialogues via Document Semantic Graphscited by 11
  5. 2023Coarse-to-Fine Knowledge Selection for Document Grounded Dialogscited by 6
  6. 2024KS-LLM: Knowledge Selection of Large Language Models with Evidence Document for Question Answeringcited by 4
  7. 2024A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Less is More: Compact Clue Selection for Efficient Retrieval-Augmented Generation Reasoningcited by 1
  2. 2026Context Selection for Hypothesis and Statistical Evidence Extraction from Full-Text Scientific Articlescited by 0
  3. 2026ANN Search: Recall What Matterscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Is Relevance Propagated from Retriever to Generator in RAG?
  2. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generation
  3. 2025RAGTrace: Understanding and Refining Retrieval-Generation Dynamics in Retrieval-Augmented Generation
  4. 2025Enhancing Retrieval-Augmented Generation: A Study of Best Practices
  5. 2025Dynamic and Parametric Retrieval-Augmented Generation
  6. 2024A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions
  7. 2024Understanding the Fundamental Design Decisions of Retrieval-Augmented Generation Systems
  8. 2024Evaluation of Retrieval-Augmented Generation: A Survey