# Less LLM, More Documents: Searching for Improved RAG

arXiv: https://arxiv.org/abs/2510.02657 · HTML: https://mlsanity.com/paper/2510.02657/

## Key facts

- Cited by 4 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 29 of its 37 references that are in the map.
- First posted on arXiv 3 Oct 2025.

## Placed in

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

## Builds on (most cited first, 29 of 29)

- [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)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies](https://mlsanity.com/paper/2404.06395/) (2024)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://mlsanity.com/paper/2102.07350/) (2021)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction](https://mlsanity.com/paper/2112.01488/) (2021)
- [A Survey on Model Compression for Large Language Models](https://mlsanity.com/paper/2308.07633/) (2023)
- [Scaling Laws for Neural Machine Translation](https://mlsanity.com/paper/2109.07740/) (2021)
- [On-Device Language Models: A Comprehensive Review](https://mlsanity.com/paper/2409.00088/) (2024)
- [A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions](https://mlsanity.com/paper/2410.12837/) (2024)
- [Model Compression and Efficient Inference for Large Language Models: A Survey](https://mlsanity.com/paper/2402.09748/) (2024)
- [Scaling Retrieval-Based Language Models with a Trillion-Token Datastore](https://mlsanity.com/paper/2407.12854/) (2024)
- [DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research](https://mlsanity.com/paper/2505.19253/) (2025)
- [Enhancing Retrieval-Augmented Generation: A Study of Best Practices](https://mlsanity.com/paper/2501.07391/) (2025)
- [ClueWeb22: 10 Billion Web Documents with Visual and Semantic Information](https://mlsanity.com/paper/2211.15848/) (2022)
- [Position Engineering: Boosting Large Language Models through Positional Information Manipulation](https://mlsanity.com/paper/2404.11216/) (2024)
- [On the Influence of Context Size and Model Choice in Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2502.14759/) (2025)

## Built on by (most cited first, 4 of 4)

- [Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines](https://mlsanity.com/paper/2604.01029/) (2026)
- [Same Agent, Different Answers: A Repeat-Aware Audit of Corpus-Induced Answer Churn in Retrieval-Augmented QA](https://mlsanity.com/paper/2608.22856/) (2026)
- [Retrieval-Augmented Generation in LLMs for Mental Health: Quantifying the Incremental Contribution of Retrieval Within a Layered Safety Architecture](https://mlsanity.com/paper/2607.24817/) (2026)
- [Narrow and Deep: An Ontology Tower as the Knowledge of an LLM Agent for an Industrial Equipment System](https://mlsanity.com/paper/2610.11768/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) couples document retrieval with large language models (LLMs). While scaling generators often improves accuracy, it also increases inference and deployment overhead. We study an orthogonal axis: enlarging the retriever's corpus, and how it trades off with generator scale. Across multiple open-domain QA benchmarks, corpus scaling consistently strengthens RAG and can in many cases match the gains of moving to a larger model tier, though with diminishing returns at larger scales. Small- and mid-sized generators paired with larger corpora often rival much larger models with smaller corpora; mid-sized models tend to gain the most, while tiny and very large models benefit less. Our analysis suggests that these improvements arise primarily from increased coverage of answer-bearing passages, while utilization efficiency remains largely unchanged. Overall, our results characterize a corpus-generator trade-off in RAG and provide empirical guidance on how corpus scale and model capacity interact in this setting.