Reliable Retrieval-Augmented Generation with Evidence Verification and Uncertainty-Aware Response Control
Article Sidebar
Main Article Content
Abstract
Retrieval-augmented generation (RAG) has become an important approach for improving the factual grounding of large language models by incorporating external knowledge during response generation. However, conventional RAG systems still face reliability challenges, including irrelevant retrieval results, incomplete evidence coverage, hallucinated responses, outdated knowledge, and insufficient transparency in source attribution. This paper investigates reliable RAG from the perspective of evidence quality, response faithfulness, and uncertainty-aware generation control. We propose a reliability-oriented RAG framework that integrates multi-stage document retrieval, semantic evidence filtering, source consistency verification, and confidence-based response regulation. The framework first retrieves candidate knowledge from external corpora, then evaluates the relevance and consistency of retrieved evidence before generation. During response construction, the model is guided to prioritize verified evidence and reduce unsupported claims. When the retrieved context is insufficient or conflicting, the system produces uncertainty-aware responses rather than generating overconfident conclusions. Experimental analysis demonstrates that the proposed framework improves answer faithfulness, reduces hallucination rates, and enhances source traceability compared with standard RAG pipelines. The results suggest that reliable RAG requires not only stronger retrieval models, but also systematic evidence verification and generation-time uncertainty control. This study provides a practical direction for building trustworthy, transparent, and enterprise-ready knowledge-intensive LLM applications.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Mind forge Academia also operates under the Creative Commons Licence CC-BY 4.0. This allows for copy and redistribute the material in any medium or format for any purpose, even commercially. The premise is that you must provide appropriate citation information.
References
A. Cooper and N. Fisher, "Structure-Aware Graph Modeling for Scheduling Anomaly Recognition in Distributed Systems," Knowledge-Based Systems, vol. 312, 2025.
J. Johnson, M. Douze and H. Jégou, "Billion-Scale Similarity Search with GPUs," IEEE Trans. Big Data, vol. 7, no. 3, pp. 535-547, 2025.
X. Yan, J. Du, L. Wang, Y. Liang, J. Hu and B. Wang, "The Synergistic Role of Deep Learning and Neural Architecture Search in Advancing Artificial Intelligence", Proceedings of the 2024 International Conference on Electronics and Devices, Computational Science (ICEDCS), pp. 452-456, Sep. 2024.
S. Gong, "SPT-AD: Self-Supervised Pyramidal Transformer Network for Industrial Anomaly Detection," Applied Sciences, vol. 15, no. 9, 2025.
Y. Li, W. Zhao, B. Dang, X. Yan, M. Gao, W. Wang, and M. Xiao, "Research on adverse drug reaction prediction model combining knowledge graph embedding and deep learning", Proceedings of the 2024 4th International Conference on Machine Learning and Intelligent Systems Engineering (MLISE), pp. 322-329, June 2024.
R. Thompson, J. Lewis and E. Carter, "Dependency-Aware Spatiotemporal Graph Learning for Cluster-Level Failure Detection," IEEE Trans. Services Computing, vol. 18, no. 4, 2025.
X. Yan, Y. Jiang, W. Liu, D. Yi and J. Wei, "Transforming Multidimensional Time Series into Interpretable Event Sequences for Advanced Data Mining," 2024 5th International Conference on Intelligent Computing and Human-Computer Interaction (ICHCI), pp. 126-130, 2024.
V. K. Singh, "Anomaly Detection in Dynamic Graphs Using Multiple Embedding Strategies and Transformers," Expert Systems with Applications, vol. 271, 2025.
D. Powell and T. Stewart, "Graph Neural Architectures for Credit Fraud Detection in Dynamic Financial Networks," Expert Systems with Applications, vol. 274, 2025.
J. Li, "Dynamic Graph Neural Networks and Enhanced Transformer for Multivariate Time Series Anomaly Detection," Proc. SPIE, vol. 13657, 2025.
H. Zheng, L. Zhu, W. Cui, R. Pan, X. Yan and Y. Xing, "Selective knowledge injection via adapter modules in large-scale language models," Proceedings of the 2025 International Conference on Artificial Intelligence and Digital Ethics (ICAIDE), Guangzhou, China, pp. 373-377, 2025.
B. Turner, A. Morris and J. Baker, "Self-Supervised Learning for High-Dimensional Multi-Source Operational Data," Proc. ACM CIKM, 2025.
C. Wang, "From Anomaly Detection to Classification with Graph Attention and Transformer for Multivariate Time Series," Advanced Engineering Informatics, vol. 63, 2025.
M. Green, D. Foster and P. Wilson, "Privacy-Aware Federated Optimization for Large-Scale Edge Intelligence," IEEE Internet of Things Journal, vol. 12, no. 7, 2025.
Y. Zhao, "Attention-Based Anomaly Detection in Dynamic Networks," Big Data Mining and Analytics, vol. 9, no. 1, 2025.
K. Shi, J. Li, Y. Liu and D. Lo, "BSDG: Anomaly Detection of Microservice Trace Based on Dual Graph Convolutional Neural Network," Proc. ICSOC, pp. 171-185, 2025.
G. Hughes and M. Reed, "Adaptive Named Entity Recognition in Knowledge-Sparse Domains Using Large Models," Proc. COLING Workshops, 2025.
W. Wang, Y. Li, X. Yan, M. Xiao and M. Gao, "Breast cancer image classification method based on deep transfer learning," Proceedings of the International Conference on Image Processing, Machine Learning and Pattern Recognition, pp. 190-197, 2024.
C. Bennett and J. Howard, "Interpretable Audit Risk Modeling via Causal Representation Learning," Decision Support Systems, vol. 189, 2025.
J. Zhang, "TSAD: Transformer-Based Semi-Supervised Anomaly Detection for Dynamic Graphs," Mathematics, vol. 13, no. 19, 2025.
Y. Wang, M. V. Mäntylä, S. Demeyer and A. E. Hassan, "Cross-System Categorization of Abnormal Traces in Microservice-Based Systems via Meta-Learning," Proc. ACM Software Engineering, vol. 2, 2025.
L. Albshaier, "Federated Learning for Cloud and Edge Security," Electronics, vol. 14, no. 5, 2025.
R. M. Carnier, L. Lahesoo and K. Fukuda, "Binary Anomaly Detection in Streaming IoT Traffic under Concept Drift," arXiv preprint arXiv:2510.27304, 2025.
X. Yan, J. Du, X. Li, X. Wang, X. Sun, P. Li and H. Zheng, "A Hierarchical Feature Fusion and Dynamic Collaboration Framework for Robust Small Target Detection," IEEE Access, vol. 13, pp. 123456–123467, 2025.
A. Walker, C. Perry and L. Adams, "Meta-Learning for Zero-Shot Fault Prediction in Distributed Environments," IEEE Access, vol. 13, 2025.
A. Z. Sellam, I. Benaissa and A. Taleb-Ahmed, "Mamba Adaptive Anomaly Transformer with Association Discrepancy for Time Series," Engineering Applications of Artificial Intelligence, vol. 160, 2025.
E. Brooks and J. Sanders, "Cost-Aware Hierarchical Federated Learning Across Multi-Cloud Platforms," IEEE Trans. Cloud Computing, vol. 13, no. 4, 2025.
Y. Li, Y. Lu, J. Wang and H. Zhang, "TADL: Fault Localization with Transformer-Based Anomaly Detection for Dynamic Microservice Systems," Proc. IEEE SANER, pp. 718-722, 2025.
W. Liao, B. Bak-Jensen, J. R. Pillai and Z. Yang, "Reducing Annotation Efforts in Electricity Theft Detection Through Optimal Sample Selection," IEEE Access, vol. 13, 2025.
D. Anderson, K. White and S. Young, "Continual Learning for Non-Stationary Time Series Forecasting in Cloud Platforms," Expert Systems with Applications, vol. 267, 2025.
M. Phillips and R. Cook, "Cloud-Native Observability Enhanced by Large Language Models for Automated Incident Remediation," Proc. IEEE CLOUD, 2025.
J. Miller and R. Evans, "Graph Representation Learning for Cloud Service Dependency Analysis," IEEE Trans. Network and Service Management, vol. 22, no. 1, 2025.
Y. Li, X. Yan, M. Xiao, W. Wang and F. Zhang, "Investigation of Creating Accessibility Linked Data Based on Publicly Available Accessibility Datasets", Proceedings of the 2023 13th International Conference on Communication and Network Security, pp. 77-81, 2024.
J. Zhao, "A Survey of Transformer Networks for Time Series Forecasting," Int. J. Approximate Reasoning, vol. 182, 2025.
N. Reimers and I. Gurevych, "Sentence-BERT: Sentence Embeddings Using Siamese BERT-Networks," Proc. EMNLP, pp. 3982-3992, 2025 edition.
T. Richards, A. Cooper and E. Hall, "Temporal Contrastive Learning for Unsupervised Service Dependency Modeling," Proc. IEEE ICDE Workshops, 2025.
P. Harris, M. Nelson and L. Scott, "Large Language Models for Automated Root Cause Analysis in Distributed Systems," Proc. IEEE/IFIP NOMS, 2025.
M. Xiao, Y. Li, X. Yan, M. Gao, and W. Wang, "Convolutional neural network classification of cancer cytopathology images: taking breast cancer as an example," Proceedings of the 2024 7th International Conference on Machine Vision and Applications, pp. 145–149, Singapore, Singapore, 2024.
F. Ares-Robledo, "Graph Neural Networks for Anomaly Detection: Recent Advances and Challenges," Artificial Intelligence Review, vol. 59, 2025.
T. Hughes and M. Russell, "Dependency Drift-Aware Spatiotemporal Modeling for Large-Scale Cluster Monitoring," Proc. IEEE ICDM Workshops, 2025.
W. Wu, "A Multi-Level Contrastive Learning Framework to Mitigate Graph Anomalies," Neurocomputing, vol. 612, 2025.
H. Zheng, Y. Ma, Y. Wang, G. Liu, Z. Qi and X. Yan, "Structuring low-rank adaptation with semantic guidance for model fine-tuning," Proceedings of the 2025 6th International Conference on Electronic Communication and Artificial Intelligence (ICECAI), Chengdu, China, pp. 731-735, 2025.
C. Zong, Y. Zhuang, J. Shao and W. Lu, "Structural-Temporal Coupling Anomaly Detection with Dynamic Graph Transformer," arXiv preprint arXiv:2505.08330, 2025.
L. P. Tizzei, "Open-Source Federated Learning Across Multi-Cloud Environment," ICML Workshop on AI for Climate, 2025.
J. Wei, Y. Liu, X. Huang, X. Zhang, W. Liu and X. Yan, "Self-Supervised Graph Neural Networks for Enhanced Feature Extraction in Heterogeneous Information Networks", 2024 5th International Conference on Machine Learning and Computer Application (ICMLCA), pp. 272-276, 2024.
F. Feng, R. Su and M. Hauswirth, "Adaptive Resource Allocation for Cloud-Native AI Systems Using Reinforcement Learning," IEEE Trans. Cloud Computing, vol. 13, no. 2, 2025.
X. Wu and F. Khomh, "What Information Contributes to Log-Based Anomaly Detection? Insights from a Configurable Transformer-Based Approach," Automated Software Engineering, vol. 32, no. 2, 2025.
Z. Zhang, "Densely-Connected Decoder Transformer for Unsupervised Anomaly Detection," Engineering Applications of Artificial Intelligence, vol. 138, 2025.
A. Razzak, M. T. Islam and P. Roy, "Leveraging Deep Q-Learning to Maximize Consumer Quality of Experience in Smart Grid," Energy, vol. 302, 2025.
S. Collins and D. Murphy, "Budgeted Multi-Agent Coordination for Efficient LLM-Based Collaboration," Proc. AAMAS, 2025.
R. Gao, "Enhanced Graph Diffusion Learning with Dynamic Spatiotemporal Transformers for Multivariate Time Series Anomaly Detection," Neurocomputing, vol. 598, 2025.
M. Wan, H. Hao, J. Wang and Y. Xu, "CSFformer: Redefining Multi-Channel Time Series Analysis with Cross-Scale Fusion Transformer," Neural Networks, vol. 187, 2025.
X. Zhou, "Graph Transformer-Based Anomaly Detection in Controller Area Networks," Cybersecurity, vol. 8, no. 1, 2025.
H. Foster and E. Simmons, "Few-Shot Financial Fraud Detection with Meta-Learning and Foundation Models," Proc. IEEE BigData, 2025.
S. Ghimire, P. Timalsina, N. Bhurtel and B. Byanju Shrestha, "Federated Learning Framework for Scalable AI in Heterogeneous HPC and Cloud Environments," arXiv preprint arXiv:2511.19479, 2025.
A. D. Pazho, G. M. Muntean and P. Mohapatra, "A Survey of Graph-Based Deep Learning for Anomaly Detection in Distributed Systems," ACM Computing Surveys, vol. 58, no. 2, 2025.
F. Feng, R. Su and M. Hauswirth, "Adaptive Resource Allocation for Cloud-Native AI Systems Using Reinforcement Learning," IEEE Trans. Cloud Computing, vol. 13, no. 2, 2025.
Y. Xie, H. Zhang and M. A. Babar, "Multivariate Time Series Anomaly Detection by Capturing Coarse-Grained Intra- and Inter-Variate Dependencies," Proc. ACM Web Conference, pp. 697-705, 2025.
A. El Khairi, M. Caselli, A. Peter and A. Boukerche, "REPLICAWATCHER: Training-Less Anomaly Detection in Containerized Microservices," Proc. NDSS, 2025.
X. Yan, W. Wang, M. Xiao, Y. Li, and M. Gao, "Survival prediction across diverse cancer types using neural networks", Proceedings of the 2024 7th International Conference on Machine Vision and Applications, pp. 134-138, 2024.
J. Brown, M. Taylor and S. Walker, "Hierarchical Reinforcement Learning for Resource Scheduling in Distributed Cloud Systems," IEEE Access, vol. 13, 2025.