mlsanityData to 13 Oct 2026

GRACE-RAG: Governed Retrieval Architecture for Canonical Evidence Synthesis, Enabling Lightweight Deployment in Closed-Domain Institutional Settings

arXiv 2607.00013 ↗First posted 8 May 2026cs.IR cs.AIcited by 0

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) systems are widely used in institutional question answering settings where responses must be grounded in authoritative documentation (Gao et al., 2023). In entity-dense domains where relevant information is distributed across heterogeneous documents, vector-only retrieval often produces fragmented evidence and increases dependence on inference-time reasoning (Zhao et al., 2024). This paper introduces GRACE-RAG, a retrieval-governed, graph-augmented RAG architecture that externalizes structural reasoning from the generative stage to a structured retrieval layer, resolving structural ambiguity offline, enabling deployment on self-hosted lightweight models calibrated to closed-domain institutional vocabulary. Experiments across three model capacities: Mistral 24B, GPT OSS 120B, and Gemini 2.5 Flash show consistent improvements in completeness, depth, and anticipatory coverage, with overall quality gains of up to 20% under mid-scale models, indicating that retrieval architecture governs structural quality over model scale, reducing computational and latency footprint without dependence on proprietary systems.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 11 of its 16 references that are in the map. First posted on arXiv 8 May 2026.

Builds on

11 of 16 references.

References · 11

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,221
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,492
  3. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,196
  4. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,594
  5. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 353
  6. 2024Graph Retrieval-Augmented Generation: A Surveycited by 321
  7. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 146
  8. 2024LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domaincited by 116
  9. 2024A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directionscited by 70
  10. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 35
  11. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Surveycited by 18

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026SF-RAG: Structure-Fidelity Retrieval-Augmented Generation for Academic Question Answering
  2. 2025Fishing for Answers: Exploring One-shot vs. Iterative Retrieval Strategies for Retrieval Augmented Generation
  3. 2026Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning
  4. 2026When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering
  5. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  6. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  7. 2025RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning
  8. 2026Why Retrieval-Augmented Generation Fails: A Graph Perspective