Authors : Sanchita H.; Skandamahima V. M.; Akshitha Katkeri

Volume/Issue : Volume 11 - 2026, Issue 9 - September

Google Scholar : https://tinyurl.com/3u7yvmvh

DOI : https://doi.org/10.38124/ijisrt/26sep724

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : responses depending on domain, retriever quality, and model family. This paper reviews the literature on why RAG systems continue to hallucinate even when correct evidence is available in context, organizes the reported causes into a five-part taxonomy (retrieval failure, conflicting evidence, unfaithful generation, over-reliance on parametric memory, and stale source content), and surveys the detection methods (NLI-based faithfulness scoring, LLM-as-judge, internal-state probing, evidence-graph consistency) and mitigation strategies (corrective retrieval, self-reflective generation, verification loops, faithfulness fine-tuning) proposed against each cause. We synthesize benchmark statistics across RAGTruth, RAGBench, and HalluRAG, and close with open challenges: the absence of a standardized evaluation protocol, the compounding of hallucination in multi-hop and agentic RAG, and the persistent gap between embedding-based detectors and reliable detection under real, model-generated hallucinations.

Keywords : Retrieval-Augmented Generation, Hallucination, Faithfulness, Factuality Detection, Ragtruth, Evaluation Benchmarks.

References :

1. P. Lewis et al., “Retrieval-augmented generation for knowledge-intensive NLP tasks,” Advances in Neural Information Processing Systems, vol. 33, pp. 9459–9474, 2020.
2. Y. Niu et al., “RAGTruth: A hallucination corpus for developing trustworthy retrieval-augmented generation models,” arXiv:2401.00396, 2024.
3. L. Huang et al., “A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions,” ACM Transactions on Information Systems, vol. 43, no. 2, 2025.
4. Z. Ji et al., “Survey of hallucination in natural language generation,” ACM Computing Surveys, vol. 55, no. 12, pp. 1–38, 2023.
5. RAGBench component study, “RAGBench: Explainable benchmark for retrieval-augmented generation systems,” arXiv:2407.11005, 2024.
6. HalluRAG, “Detecting closed-domain hallucinations in RAG applications using an LLM's internal states,” arXiv:2412.17056, 2024.
7. A. Asai, Z. Wu, Y. Wang, A. Sil, and H. Hajishirzi, “Self-RAG: Learning to retrieve, generate, and critique through self-reflection,” in Proc. ICLR, 2024.
8. S. Yan et al., “Corrective retrieval augmented generation,” arXiv:2401.15884, 2024.
9. S. Dhuliawala et al., “Chain-of-verification reduces hallucination in large language models,” in Findings of ACL, pp. 3563–3578, 2024.
10. “Retromorphic testing with hierarchical verification for hallucination detection in RAG,” arXiv:2603.27752, 2026.
11. “The semantic illusion: Certified limits of embedding-based hallucination detection in RAG systems,” arXiv:2512.15068, 2026.
12. “FVA-RAG: Falsification-verification alignment for mitigating sycophantic hallucinations,” arXiv:2512.07015, 2026.
13. “When LLMs invent Rust crates: An empirical study of hallucination patterns and mitigation,” arXiv:2606.08444, 2026.
14. “Do benchmarks underestimate LLM performance? Evaluating hallucination detection with LLM-first human-adjudicated assessment,” arXiv:2605.08462, 2026.
15. S. Es, J. James, L. Espinosa Anke, and S. Schockaert, “RAGAS: Automated evaluation of retrieval augmented generation,” in Proc. EACL System Demonstrations, pp. 150–158, 2024.
16. J. Chen, H. Lin, X. Han, and L. Sun, “Benchmarking large language models in retrieval-augmented generation,” in Proc. AAAI Conf. on Artificial Intelligence, vol. 38, pp. 17754–17762, 2024.
17. S. Min et al., “FActScore: Fine-grained atomic evaluation of factual precision in long form text generation,” in Proc. EMNLP, pp. 12076–12100, 2023.
18. T. Vu et al., “FreshLLMs: Refreshing large language models with search engine augmentation,” in Findings of ACL, pp. 13697–13720, 2024.
19. N. F. Liu et al., “Lost in the middle: How language models use long contexts,” Transactions of the Association for Computational Linguistics, vol. 12, pp. 157–173, 2024.
20. V. Adlakha, P. BehnamGhader, X. H. Lu, N. Meade, and S. Reddy, “Evaluating correctness and faithfulness of instruction-following models for question answering,” Transactions of the Association for Computational Linguistics, vol. 12, pp. 681–699, 2024.