mlsanityData to 14 Oct 2026

CiteGuard-RAG: A Validation-Centered AI System for Evidence-Grounded Question Answering

arXiv 2609.15830 ↗First posted 14 Sep 2026cs.CL cs.AI cs.IRcited by 0

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

Abstract (arXiv)

Retrieval-augmented generation (RAG) can improve access to complex information; however, retrieving evidence alone does not ensure that answers are grounded, citation-valid, or appropriately refused. This paper introduces CiteGuard-RAG, a validation-centered AI system for evidence-grounded question answering. The system integrates hybrid semantic-lexical retrieval, citation-constrained generation, sentence-level grounding validation, and single-pass regeneration. Validation is used at runtime to determine whether a candidate answer should be accepted, refused, or regenerated before final delivery. CiteGuard-RAG is evaluated on 400 questions across a controlled housing-law dataset, PrivacyQA, and CUAD. In the controlled evaluation, it achieves 99.1% retrieval accuracy, 98.3% grounded-answer accuracy, and 98.3% citation validity, with no validation-detected hallucinations. Ablation results show that grounded-answer accuracy drops sharply when validation is removed, even when retrieval accuracy remains unchanged. External evaluation shows that while citation validity remains strong, evidence utilization, span alignment, and refusal calibration become harder under domain shift. These findings indicate that trustworthy RAG systems require explicit validation between retrieval and final answer delivery. CiteGuard-RAG provides a practical architecture for linking retrieval, generation, citation checking, abstention, and regeneration in high-stakes information access.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 22 of its 29 references that are in the map. First posted on arXiv 14 Sep 2026.

Builds on

22 of 29 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Benchmarking Large Language Models in Retrieval-Augmented Generation4 Sep

Other references · 21

  1. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  2. 2023Qwen Technical Reportcited by 3,344
  3. 2023Mistral 7Bcited by 3,164
  4. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  5. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  6. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  7. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  8. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  9. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 578
  10. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 452
  11. 2021CUAD: An Expert-Annotated NLP Dataset for Legal Contract Reviewcited by 236
  12. 2023Recommender Systems in the Era of Large Language Models (LLMs)cited by 189
9 more
  1. 2024Evaluating Retrieval Quality in Retrieval-Augmented Generationcited by 90
  2. 2023Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedbackcited by 72
  3. 2019Question Answering for Privacy Policies: Combining Computational and Legal Perspectivescited by 67
  4. 2023MultiLegalPile: A 689GB Multilingual Legal Corpuscited by 60
  5. 2024M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitionscited by 38
  6. 2022Mining Legal Arguments in Court Decisionscited by 35
  7. 2024Retrieval-augmented generation in multilingual settingscited by 27
  8. 2023LLMEval: A Preliminary Study on How to Evaluate Large Language Modelscited by 23
  9. 2023Retrieval for Extremely Long Queries and Documents with RPRS: a Highly Efficient and Effective Transformer-based Re-Rankercited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025VeriCite: Towards Reliable Citations in Retrieval-Augmented Generation via Rigorous Verification
  2. 2026PAVE: Premise-Aware Validation and Editing for Retrieval-Augmented LLMs
  3. 2026SURE-RAG: Sufficiency and Uncertainty-Aware Evidence Verification for Selective Retrieval-Augmented Generation
  4. 2026RAG-Stress: Probing the Limits of Evidence Reliance in Retrieval-Augmented Generation
  5. 2026Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning
  6. 2026AB-RAG: Adaptive Budgeted Retrieval-Augmented Generation for Reliable Question Answering
  7. 2026GRACE-RAG: Governed Retrieval Architecture for Canonical Evidence Synthesis, Enabling Lightweight Deployment in Closed-Domain Institutional Settings
  8. 2026ProvenAI: Provenance-Native Traces of Evidence in Generated Answers