mlsanityData to 7 Oct 2026

Covering the Unseen: Information Demand Coverage Optimization for Retrieval-Augmented Generation

arXiv 2606.29328 ↗First posted 28 Jun 2026cs.IR cs.AIcited by 0

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

Abstract (arXiv)

Retrieval-augmented generation (RAG) typically treats context selection as ranking chunks against a single query embedding. This assumption breaks down for complex queries, such as multi-hop or ambiguous questions, where top-k selection tends to over-cover one semantic aspect while ignoring critical sub-questions. We propose GeoRAG, which recasts context selection as Information Demand Coverage Optimization. GeoRAG builds a multi-dimensional demand distribution through diverse sub-query generation and reverse-validation weighting, then selects context by minimizing the Sinkhorn-Wasserstein distance between this demand distribution and the coverage of the selected set. The resulting demand-weighted facility-location objective is monotone submodular, giving a 1-1/e greedy guarantee, which we approximate with a Sinkhorn-based marginal-gain surrogate. The method is unsupervised, training-free, and retrieval-agnostic. We further show that single-point, query-proximity scorers cannot cover multi-modal demands, exposing a structural limit of ranking-based selection. On six open-domain QA benchmarks, GeoRAG improves exact match (EM) by +6.5 to +7.5 points over top-k truncation (up to +9.7 on HotpotQA and ASQA) and outperforms strong baselines including MMR, DPP, BGE-Reranker, SMART-RAG, and AdaGReS, with stable gains across context budgets and sub-query generators.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 17 of its 29 references that are in the map. First posted on arXiv 28 Jun 2026.

Builds on

17 of 29 references.

Closest ancestors · 5

Same direction, newest first

  1. 2026Scaling DPPs for RAG: Density Meets Diversity4 Feb
  2. 2025Cracking Vector Search Indexes3 Mar
  3. 2024SMART-RAG: Selection using Determinantal Matrices for Augmented Retrieval21 Sep
  4. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research22 May
  5. 2024RAG-Fusion: a New Take on Retrieval-Augmented Generation31 Jan

Other references · 12

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  4. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  5. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
  6. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  7. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 200
  8. 2023Survey of Vector Database Management Systemscited by 38
  9. 2025InfoGain-RAG: Boosting Retrieval-Augmented Generation via Document Information Gain-based Reranking and Filteringcited by 8
  10. 2025AdaGReS:Adaptive Greedy Context Selection via Redundancy-Aware Scoring for Token-Budgeted RAGcited by 6
  11. 2024VDTuner: Automated Performance Tuning for Vector Data Management Systemscited by 5
  12. 2026OptiSet: Unified Optimizing Set Selection and Ranking for Retrieval-Augmented Generationcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Search for Coverage: Learning Coverage-Aware Retrieval with Augmented Sub-Question Answerability
  2. 2025Dynamic Context Selection for Retrieval-Augmented Generation: Mitigating Distractors and Positional Bias
  3. 2024RichRAG: Crafting Rich Responses for Multi-faceted Queries in Retrieval-Augmented Generation
  4. 2026One Size Does Not Fit All! Dynamic Retriever and Generator Selection for RAG
  5. 2024EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation
  6. 2026Rethinking Retrieval-Augmentation as Synthesis: A Query-Aware Context Merging Approach
  7. 2025mmRAG: A Modular Benchmark for Retrieval-Augmented Generation over Text, Tables, and Knowledge Graphs
  8. 2026Tail-Aware Adaptive-k: Query-Adaptive Context Selection for Retrieval-Augmented Generation