# Large Document Collections Reduce RAG Accuracy, Study Finds

> Adding more heterogeneous documents hurt retrieval‑augmented generation performance, with precision dropping 63% in a test.

Oossa · 2026-10-15 · https://oossa.com/en/large-document-collections-reduce-rag-accuracy-study-finds

Researchers led by Nabaraj Subedi examined retrieval‑augmented generation (RAG) on growing document sets. In a Wyoming DOT system, expanding the corpus from 54 to 1,128 documents cut precision@10 by 63% and lowered recall of the answer‑bearing document by 23%. The paper proposes a soft‑scoping technique that limits retrieval to relevant domains without extra training. The authors recommend applying soft scoping first, then using a single synthesis call.

## The facts

- Corpus grew from 54 to 1,128 documents, precision@10 fell 63%, recall fell 23%
- Paper posted on arXiv on 2026-10-15 ("Thu Oct 15 2026 06:00:00 GMT+0200")

## Why it matters

For developers of RAG‑based chatbots, adding more documents can actually make answers less accurate unless domain scoping is used.

## Sources & references

1. [When More Documents Hurt RAG: Measuring and Reducing Vector Search Dilution with Domain-Scoped Retrieval](https://arxiv.org/abs/2606.11350) – arXiv cs.IR, 2026-10-15

Last updated: 2026-10-15