mlsanityData to 7 Oct 2026

Mitigating LLM Hallucinations through Domain-Grounded Tiered Retrieval

arXiv 2603.17872 ↗First posted 18 Mar 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have achieved unprecedented fluency but remain susceptible to "hallucinations" - the generation of factually incorrect or ungrounded content. This limitation is particularly critical in high-stakes domains where reliability is paramount. We propose a domain-grounded tiered retrieval and verification architecture designed to systematically intercept factual inaccuracies by shifting LLMs from stochastic pattern-matchers to verified truth-seekers. The proposed framework utilizes a four-phase, self-regulating pipeline implemented via LangGraph: (I) Intrinsic Verification with Early-Exit logic to optimize compute, (II) Adaptive Search Routing utilizing a Domain Detector to target subject-specific archives, (III) Refined Context Filtering (RCF) to eliminate non-essential or distracting information, and (IV) Extrinsic Regeneration followed by atomic claim-level verification. The system was evaluated across 650 queries from five diverse benchmarks: TimeQA v2, FreshQA v2, HaluEval General, MMLU Global Facts, and TruthfulQA. Empirical results demonstrate that the pipeline consistently outperforms zero-shot baselines across all environments. Win rates peaked at 83.7% in TimeQA v2 and 78.0% in MMLU Global Facts, confirming high efficacy in domains requiring granular temporal and numerical precision. Groundedness scores remained robustly stable between 78.8% and 86.4% across factual-answer rows. While the architecture provides a robust fail-safe for misinformation, a persistent failure mode of "False-Premise Overclaiming" was identified. These findings provide a detailed empirical characterization of multi-stage RAG behavior and suggest that future work should prioritize pre-retrieval "answerability" nodes to further bridge the reliability gap in conversational AI.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 41 references that are in the map. First posted on arXiv 18 Mar 2026.

Builds on

31 of 41 references.

References · 31

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  4. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  5. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  7. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  8. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  9. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  10. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 578
  11. 2021SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarizationcited by 402
  12. 2023HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Modelscited by 329
19 more
  1. 2024Hallucination is Inevitable: An Innate Limitation of Large Language Modelscited by 329
  2. 2023FreshLLMs: Refreshing Large Language Models with Search Engine Augmentationcited by 308
  3. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 272
  4. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documentscited by 251
  5. 2023FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarioscited by 247
  6. 2025Why Language Models Hallucinatecited by 205
  7. 2024Corrective Retrieval Augmented Generationcited by 187
  8. 2021A Dataset for Answering Time-Sensitive Questionscited by 150
  9. 2023The Troubling Emergence of Hallucination in Large Language Models -- An Extensive Definition, Quantification, and Prescriptive Remediationscited by 130
  10. 2024Reducing hallucination in structured outputs via Retrieval-Augmented Generationcited by 92
  11. 2024LLMs Will Always Hallucinate, and We Need to Live With Thiscited by 77
  12. 2025Large Language Models Hallucination: A Comprehensive Surveycited by 45
  13. 2025Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learningcited by 39
  14. 2025The Distracting Effect: Understanding Irrelevant Passages in RAGcited by 32
  15. 2024Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspectivecited by 29
  16. 2025DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generationcited by 14
  17. 2024LLMs: A Game-Changer for Software Engineers?cited by 11
  18. 2024Exploring ChatGPT and its Impact on Societycited by 6
  19. 2024Investigating the Role of Prompting and External Tools in Hallucination Rates of Large Language Modelscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning
  2. 2025HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation
  3. 2025Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Models
  4. 2025Beyond Facts: Evaluating Intent Hallucination in Large Language Models
  5. 2025REFIND at SemEval-2025 Task 3: Retrieval-Augmented Factuality Hallucination Detection in Large Language Models
  6. 2024Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output
  7. 2024Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases
  8. 2025Stemming Hallucination in Language Models Using a Licensing Oracle