When More Documents Hurt RAG: Mitigating Vector Search Dilution with Domain-Scoped, Model-Agnostic Retrieval

Nabaraj Subedi, Ahmed Abdelaty, Shivanand Venkanna Sheshappanavar

Retrieval-augmented generation degrades when scaled to large, heterogeneous document collections, where dense similarity loses discriminative power, and top-k retrieval increasingl…