When More Documents Hurt RAG: Mitigating Vector Search Dilution with Domain-Scoped, Model-Agnostic Retrieval
Retrieval-augmented generation degrades when scaled to large, heterogeneous document collections, where dense similarity loses discriminative power, and top-k retrieval increasingly returns semantically similar but contextually incorrect chunks. We refer to this failure mode as vector search dilution. Even when using hybrid dense+sparse retrieval, we observed this firsthand in a deployed Wyoming Department of Transportation corpus, where scaling from 54 to 1,128 documents (88,907 chunks) reduced accuracy from 75% to below 40%. To address this dilution, we propose MASDR-RAG ( Multi-Agent Scoped Domain Retrieval for RAG) and evaluate it on 200 expert-validated queries across five LLM backbones, six corpora, and two index stacks. Our results indicate that domain scoping using organizational metadata is the key fix, significantly improving P@10 from 0.77 to 0.86 ($p < 0.05$). Furthermore, our investigation of multi-agent orchestration revealed that a high degree of configuration dependence results --creating what we call the precision-faithfulness paradox. Based on these varied outcomes, our practical recommendation is simple: scope first, then perform a single synthesis call, reserving full multi-agent orchestration for genuinely multi-domain corpora paired with native-tool-call backbones. Code and Data will be made public upon acceptance.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
SOLAR: Sparse Orthogonal Learned and Random Embeddings
Dense embedding models are commonly deployed in commercial search engines, wherein all the document vectors are pre-computed, and near-neighbor search (NNS) is performed with the query vector to find relevant documents. …
Multi-Label ClassificationMUlTI-LABEL-ClASSIFICATIONVietnamese Legal Information Retrieval in Question-Answering System
In the modern era of rapidly increasing data volumes, accurately retrieving and recommending relevant documents has become crucial in enhancing the reliability of Question Answering (QA) systems. Recently, Retrieval Augm…
HallucinationInformation RetrievalQuestion AnsweringRAG+3Progressive Searching for Retrieval in RAG
Retrieval Augmented Generation (RAG) is a promising technique for mitigating two key limitations of large language models (LLMs): outdated information and hallucinations. RAG system stores documents as embedding vectors …
The Curious Case of Adversarially Robust Models: More Data Can Help, Double Descend, or Hurt Generalization
Adversarial training has shown its ability in producing models that are robust to perturbations on the input data, but usually at the expense of decrease in the standard accuracy. To mitigate this issue, it is commonly b…
ClassificationGeneral ClassificationComparing Lexical and Semantic Vector Search Methods When Classifying Medical Documents
Classification is a common AI problem, and vector search is a typical solution. This transforms a given body of text into a numerical representation, known as an embedding, and modern improvements to vector search focus …
Information Retrieval