Comparative Analysis of Confidence-Aware and Verification Based Hallucination Reduction Techniques in Retrieval-Augmented Generation Systems

A lightweight RAG experiment compared a baseline against confidence gating, answer verification, and a combined pipeline. Basic and Verification-Based RAG returned 30 correct outcomes, while the confidence-gated methods returned 29 because one relevant passage fell below the selected threshold. No unsupported final answer was observed. Verification added latency but preserved coverage; confidence gating reduced calls but required calibration. The next stage should evaluate public QA benchmarks, conflicting evidence, longer answers, model-diverse verification, and human claim-level scoring before any enterprise deployment decision.    

[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]  Z. Ji et al., “Survey of Hallucination in Natural Language Generation,” ACM Computing Surveys, vol. 55, no. 12, Art. 248, 2023, doi: 10.1145/3571730. [3]  L. Huang et al., “A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions,” ACM Transactions on Information Systems, 2025, doi: 10.1145/3703155. [4] A. Asai et al., “Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection,” Proc. ICLR, 2024. [5]  S.-Q. Yan, J.-C. Gu, Y. Zhu, and Z.-H. Ling, “Corrective Retrieval Augmented Generation,” arXiv:2401.15884, 2024. [6]  S. Dhuliawala et al., “Chain-of-Verification Reduces Hallucination in Large Language Models,” Findings of ACL, pp. 3563-3578, 2024. [7]  S. Es, J. James, L. Espinosa-Anke, and S. Schockaert, “Ragas: Automated Evaluation of Retrieval Augmented Generation,” arXiv:2309.15217, 2023. [8]  V. Karpukhin et al., “Dense Passage Retrieval for Open-Domain Question Answering,” Proc. EMNLP, pp. 6769-6781, 2020. [9]  J. Johnson, M. Douze, and H. Jégou, “Billion-Scale Similarity Search with GPUs,” IEEE Transactions on Big Data, vol. 7, no. 3, pp. 535-547, 2021. [10]  N. Reimers and I. Gurevych, “Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks,” Proc. EMNLP-IJCNLP, pp. 3982-3992, 2019.