mlsanityData to 14 Oct 2026

MODE: Mixture of Document Experts for RAG

arXiv 2509.00100 ↗First posted 27 Aug 2025cs.AIcited by 0

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) often relies on large vector databases and cross-encoders tuned for large-scale corpora, which can be excessive for small, domain-specific collections. We present MODE (Mixture of Document Experts), a lightweight alternative that replaces fine-grained nearest-neighbor search with cluster-and-route retrieval. Documents are embedded, grouped into semantically coherent clusters, and represented by cached centroids. At query time, we route to the top centroid(s) and retrieve context only within those clusters, eliminating external vector-database infrastructure and reranking while keeping latency low. On HotpotQA and SQuAD corpora with 100-500 chunks, MODE matches or exceeds a dense-retrieval baseline in answer quality while reducing end-to-end retrieval time. Ablations show that cluster granularity and multi-cluster routing control the recall/precision trade-off, and that tighter clusters improve downstream accuracy. MODE offers a practical recipe for small and medium corpora where simplicity, speed, and topical focus matter.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 8 of its 22 references that are in the map. First posted on arXiv 27 Aug 2025.

Builds on

8 of 22 references.

References · 8

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  5. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  6. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  7. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  8. 2019Passage Re-ranking with BERTcited by 645

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Cluster-based Adaptive Retrieval: Dynamic Context Selection for RAG Applications
  2. 2026When More Documents Hurt RAG: Mitigating Vector Search Dilution with Domain-Scoped, Model-Agnostic Retrieval
  3. 2026CHOP: Chunkwise Context-Preserving Framework for RAG on Multi Documents
  4. 2025Less LLM, More Documents: Searching for Improved RAG
  5. 2026Bridging OLAP and RAG: A Multidimensional Approach to the Design of Corpus Partitioning
  6. 2025mmRAG: A Modular Benchmark for Retrieval-Augmented Generation over Text, Tables, and Knowledge Graphs
  7. 2026KohakuRAG: A simple RAG framework with hierarchical document indexing
  8. 2026Evaluating Modern RAG: Textual, Multimodal, Dense, and Late Interaction Pipelines