# How Does Knowledge Selection Help Retrieval Augmented Generation?

arXiv: https://arxiv.org/abs/2410.13258 · HTML: https://mlsanity.com/paper/2410.13258/

## 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 24 of its 31 references that are in the map.
- First posted on arXiv 17 Oct 2024.

## Placed in

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

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [The Power of Noise: Redefining Retrieval for RAG Systems](https://mlsanity.com/paper/2401.14887/) (2024)
- [Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG](https://mlsanity.com/paper/2410.05983/) (2024)
- [RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2407.11005/) (2024)
- [Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue](https://mlsanity.com/paper/2002.07510/) (2020)
- [Towards Exploiting Background Knowledge for Building Conversation Systems](https://mlsanity.com/paper/1809.08205/) (2018)
- [Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?](https://mlsanity.com/paper/2406.13121/) (2024)
- [Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialog](https://mlsanity.com/paper/2102.04643/) (2021)
- [FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG](https://mlsanity.com/paper/2410.10293/) (2024)
- [Generative Knowledge Selection for Knowledge-Grounded Dialogues](https://mlsanity.com/paper/2304.04836/) (2023)
- [Enhanced Knowledge Selection for Grounded Dialogues via Document Semantic Graphs](https://mlsanity.com/paper/2206.07296/) (2022)
- [Coarse-to-Fine Knowledge Selection for Document Grounded Dialogs](https://mlsanity.com/paper/2302.11849/) (2023)
- [KS-LLM: Knowledge Selection of Large Language Models with Evidence Document for Question Answering](https://mlsanity.com/paper/2404.15660/) (2024)
- [A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation](https://mlsanity.com/paper/2403.03496/) (2024)

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

- [Less is More: Compact Clue Selection for Efficient Retrieval-Augmented Generation Reasoning](https://mlsanity.com/paper/2502.11811/) (2025)
- [Context Selection for Hypothesis and Statistical Evidence Extraction from Full-Text Scientific Articles](https://mlsanity.com/paper/2603.21193/) (2026)
- [ANN Search: Recall What Matters](https://mlsanity.com/paper/2606.04522/) (2026)

## 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.