{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T00:18:06Z","timestamp":1793751486850,"version":"4.6.1"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T00:00:00Z","timestamp":1770595200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"vor","delay-in-days":21,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Manipal Academy of Higher Education, Manipal"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Cold emailing is used to personalize, target emails for outreach without prior contact. Automating this personalized cold email generation process can significantly improve outreach efficiency for job seekers, particularly in competitive industries. It streamlines the process of composition, saves time and increases engagement, tailored to a specific industry or role. In today\u2019s competitive market, where job application is made easy, such a tool scales communication and boosts the conversion rate. The cold email generator. RAGMail, is an intelligent cold email generator that is cloud-integrated and uses Retrieval-Augmented Generation (RAG) to reduce hallucinations. The cloud-native infrastructure on which the system is built makes use of services including managed Large Language Model (LLMs) APIs, scalable vector databases, and object storage. With real-time document retrieval and cloud-hosted, metadata-aware templates, RAGMail guarantees high personalization accuracy and factual foundation. This cloud-native architecture provides elastic scalability, low-latency inference, and real-time personalization at scale, all while protecting data and user privacy with role-based access control and encrypted storage. Beyond job applications, the approach can be applied to a wide range of outreach sectors, including sales, academia, and commercial relationships, where factual accuracy and context sensitivity are critical. The system ensures high availability and load balancing during peak demand periods by utilizing distributed cloud resources. The models exhibit open-domain conversational capabilities, generalize effectively to scenarios beyond the trained data, and as verified by human evaluations, substantially reduce the well-known problem of knowledge hallucination in state-of-the-art chatbots. The proposed framework offers a scalable and reliable solution for generating contextually grounded, high-quality cold emails using Retrieval-Augmented Generation.<\/jats:p>","DOI":"10.1038\/s41598-026-38913-w","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T06:17:13Z","timestamp":1770617833000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["RAGMail: a cloud-based retrieval-augmented framework for reducing hallucinations in LLM text generation"],"prefix":"10.1038","volume":"16","author":[{"given":"Priyodip","family":"Sanyal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kumud","family":"Rathore","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R. Vijaya","family":"Arjunan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,2,9]]},"reference":[{"key":"38913_CR1","doi-asserted-by":"publisher","unstructured":"Plaisir, M. L. & Team, A. May, How To Build the Perfect Cold Email Strategy and why Creating Campaigns with a Maximum of 2 Emails (ResearchGate, (2024). https:\/\/doi.org\/10.13140\/RG.2.2.13884.62086.","DOI":"10.13140\/RG.2.2.13884.62086"},{"key":"38913_CR2","doi-asserted-by":"publisher","unstructured":"Plaisir, M L. & Team, A. Specific target: how important is personalization in cold emails. https:\/\/doi.org\/10.13140\/RG.2.2.13884.62086.","DOI":"10.13140\/RG.2.2.13884.62086"},{"key":"38913_CR3","first-page":"9459","volume":"33","author":"L \u200cP","year":"2020","unstructured":"\u200cP, L. et al. Retrieval-Augmented generation for Knowledge-Intensive NLP tasks. Adv. Neural Inform. Process. Syst. (NeurIPS). 33, 9459\u20139474 (2020).","journal-title":"Adv. Neural Inform. Process. Syst. (NeurIPS)"},{"key":"38913_CR4","doi-asserted-by":"crossref","unstructured":"Zhao, P. et al. Retrieval-augmented generation for ai-generated content: A survey. Data Sci. Eng. 2, 1\u201329 (2026 Jan).","DOI":"10.1007\/s41019-025-00335-5"},{"key":"38913_CR5","doi-asserted-by":"crossref","unstructured":"Song, J. et al. RAG-HAT: A Hallucination-Aware Tuning Pipeline for LLM in Retrieval-Augmented Generation. (2024).","DOI":"10.18653\/v1\/2024.emnlp-industry.113"},{"key":"38913_CR6","unstructured":"B\u00e9chard, P. & Orlando Marquez Ayala. and. Reducing hallucination in structured outputs via Retrieval-Augmented Generation. arXiv preprint arXiv:2404.08189 (2024)."},{"key":"38913_CR7","doi-asserted-by":"crossref","unstructured":"Wang, D., Huang, Q., Jackson, M. & Gao, J. Retrieve what you need: A mutual learning framework for open-domain question answering. Trans. Association Comput. Linguistics. 12, 24763 (2024).","DOI":"10.1162\/tacl_a_00646"},{"key":"38913_CR8","unstructured":"Raghavendran, V., Naga Satish, G., Suresh, P., Varma & Moses, G. A Study on Cloud Computing Services, (2016)."},{"key":"38913_CR9","unstructured":"Brown, T. B. B. Et al., Language Models Are Few-Shot Learners ( arXiv, Jul. 2020)."},{"key":"38913_CR10","unstructured":"Khandelwal, U., Levy, O., Jurafsky, D., Zettlemoyer, L. & Lewis, M. Generalization through Memorization: Nearest Neighbor Language Models."},{"key":"38913_CR11","unstructured":"Mallen, A. et al. When not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories, journal-article, [Online]. (2023). Available: https:\/\/arxiv.org\/pdf\/2212.10511"},{"key":"38913_CR12","doi-asserted-by":"crossref","unstructured":"Shuster, K. et al. Retrieval Augmentation Reduces Hallucination in Conversation ( arXiv, Apr. 2021).","DOI":"10.18653\/v1\/2021.findings-emnlp.320"},{"key":"38913_CR13","unstructured":"Retrieval-. Augmented Generation for AI-Generated Content: a survey."},{"key":"38913_CR14","doi-asserted-by":"crossref","unstructured":"Wu, Y. Large Language model and text generation. Cognitive Inf. Biomed. Healthcare, pp. 265\u2013297, (2024).","DOI":"10.1007\/978-3-031-55865-8_10"},{"key":"38913_CR15","doi-asserted-by":"crossref","unstructured":"Topsakal, O. & Tahir Cetin Akinci. and. Creating large language model applications utilizing langchain: A primer on developing llm apps fast. International Conference on Applied Engineering and Natural Sciences. Vol. 1. No. 1. (2023).","DOI":"10.59287\/icaens.1127"},{"key":"38913_CR16","unstructured":"Lewis, P. et al. Retrieval-Augmented Generation for Knowledge-Intensive NLP tasks, (2020)."},{"key":"38913_CR17","unstructured":"Li, H., Su, Y., Cai, D., Wang, Y. & Liu, L. A Survey on Retrieval-Augmented Text Generation."},{"key":"38913_CR18","doi-asserted-by":"crossref","unstructured":"Ram, O. et al. In-Context Retrieval-Augmented Language models. Jan (2023).","DOI":"10.1162\/tacl_a_00605"},{"key":"38913_CR19","doi-asserted-by":"crossref","unstructured":"Huang, L. et al. A survey on hallucination in large Language models: Principles, Taxonomy, Challenges, and open questions. ACM Trans. Inform. Syst. 43 (2), 1\u201355 (Jan. 2025).","DOI":"10.1145\/3703155"},{"key":"38913_CR20","unstructured":"Shuster, E. et al. Fact-Checking and Reducing Hallucination in Language Models, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 4872\u20134883, (2022)."},{"key":"38913_CR21","first-page":"1","volume":"23","author":"D Hendrycks","year":"2022","unstructured":"Hendrycks, D. et al. Aligning AI with shared human values. J. Mach. Learn. Res. 23, 1\u201335 (2022).","journal-title":"J. Mach. Learn. Res."},{"key":"38913_CR22","unstructured":"Bansal, M. et al. Challenges and Advances in RAG-based NLP Systems, Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3345\u20133357, (2023)."},{"key":"38913_CR23","unstructured":"Qin, L. et al. Large Language models Meet NLP: A survey. ArXiv Org, (2024). arxiv.org\/abs\/2405.12819"},{"key":"38913_CR24","unstructured":"Touvron, H. et al. LLAMA: Open and Efficient Foundation Language Models (arXiv:2302.13971, Feb. 2023)."},{"key":"38913_CR25","unstructured":"Zhang, Y., Cui, L., Bi, W. & Shi, S. Alleviating hallucinations of large language models through induced hallucinations."},{"key":"38913_CR26","unstructured":"M\u00fcndler, N., He, J., Jenko, S. & Vechev, M. and Department of Computer Science, ETH Zurich, Switzerland, Self-contradictory hallucinations of llms: evaluation, detection and mitigation."},{"key":"38913_CR27","doi-asserted-by":"crossref","unstructured":"Narendra, G. O. & Hashwanth, S. Named entity recognition based resume parser and summarizer. Int. J. Adv. Res. Sci. Commun. Technol. 2, 728\u2013735 (2022).","DOI":"10.48175\/IJARSCT-3029"},{"key":"38913_CR28","unstructured":"Zhang, T. et al. Mar. RAFT: Adapting Language Model to Domain Specific RAG. ArXiv (Cornell University), 15 (2024)."},{"key":"38913_CR29","doi-asserted-by":"crossref","unstructured":"Min, S. et al. FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation, Proc. EMNLP, (2023).","DOI":"10.18653\/v1\/2023.emnlp-main.741"},{"key":"38913_CR30","unstructured":"Wei, J. et al. Measuring short-form factuality in large language models. arXiv preprint arXiv :241104368 ."},{"key":"38913_CR31","doi-asserted-by":"crossref","unstructured":"Manakul, P., Schick, B., Ghorbani, K., Wang, R. & Le, H. S. H. SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models, Proc. EMNLP, (2023).","DOI":"10.18653\/v1\/2023.emnlp-main.557"},{"key":"38913_CR32","doi-asserted-by":"crossref","unstructured":"Mitra, K., Zhang, D., Rahman, S., Hruschka, E. & Factlens Benchmarking fine-grained fact verification. InFindings of the Association for Computational Linguistics: ACL 2025 Jul 18085\u201318096 . (2025).","DOI":"10.18653\/v1\/2025.findings-acl.929"},{"key":"38913_CR33","doi-asserted-by":"publisher","unstructured":"Guo, W., Wang, Y. & Jiang, P. Incentive mechanism design for federated learning with Stackelberg game perspective in the industrial scenario. Comput. Ind. Eng. 184, 109592\u2013109592. https:\/\/doi.org\/10.1016\/j.cie.2023.109592 (2023).","DOI":"10.1016\/j.cie.2023.109592"},{"key":"38913_CR34","doi-asserted-by":"publisher","first-page":"2677","DOI":"10.1109\/TIFS.2025.3544082","volume":"20","author":"Y Chen","year":"2025","unstructured":"Chen, Y. et al. Understanding the security risks of websites using cloud storage for direct user file uploads. IEEE Trans. Inf. Forensics Secur. 20, 2677\u20132692 (2025).","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"38913_CR35","doi-asserted-by":"crossref","unstructured":"Lu, H. et al. DeepAutoD: Research on distributed machine learning oriented scalable mobile communication security unpacking system. IEEE Trans. Netw. Sci. Eng. 9 (4), 2052\u20132065 (2021).","DOI":"10.1109\/TNSE.2021.3100750"},{"key":"38913_CR36","doi-asserted-by":"publisher","unstructured":"Tan, Y., Huang, W., You, Y., Su, S. & Lu, H. Recognizing BGP Communities Based on Graph Neural Network, IEEE Network, vol. 38, no. 6, pp. 282\u2013288, Jul. (2024). https:\/\/doi.org\/10.1109\/mnet.2024.3414113","DOI":"10.1109\/mnet.2024.3414113"},{"key":"38913_CR37","doi-asserted-by":"publisher","unstructured":"Gu, Z. et al. Gradient shielding: towards Understanding vulnerability of deep neural networks. IEEE Trans. Netw. Sci. Eng. 8 (2), 921\u2013932. https:\/\/doi.org\/10.1109\/tnse.2020.2996738 (2020).","DOI":"10.1109\/tnse.2020.2996738"},{"key":"38913_CR38","unstructured":"Ciccozzi, S., Wimmer, M., Cicchetti, A., Ciccozzi, F. & Berger, T. A metamodel for cloud application deployment cost estimation and optimization, Journal of Cloud Computing, vol. 12, no. 1, pp. 1\u201321, Mar. (2023)."},{"key":"38913_CR39","doi-asserted-by":"crossref","unstructured":"Stupar, I. & Huljenic, D. Model-Based Cloud Service Deployment Optimisation Method for Minimisation of Application Service Operational Cost. Journal of Cloud Computing, vol. 12, no. 1, 18 Feb. (2023).","DOI":"10.1186\/s13677-023-00389-8"},{"key":"38913_CR40","doi-asserted-by":"crossref","unstructured":"Buyya, R., Garg, S. K. & Calheiros, R. N. SLA-Oriented resource provisioning for cloud computing: Challenges, architecture, and solutions, Proceedings of the International Conference on Cloud and Service Computing (CSC), Hong Kong, China, pp. 1\u201310, 2011. [Online]., Hong Kong, China, pp. 1\u201310, 2011. [Online]. (2011).","DOI":"10.1109\/CSC.2011.6138522"},{"key":"38913_CR41","first-page":"9459","volume":"33","author":"P Lewis","year":"2020","unstructured":"Lewis, P. et al. Retrieval-augmented generation for knowledge-intensive Nlp tasks. Adv. Neural. Inf. Process. Syst. 33, 9459\u20139474 (2020).","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"38913_CR42","unstructured":"Satyaki Sanyal, N., Ghosh, SouvikHazra, S. & Adhikary Resume Parser with Natural language Processing, IJESC. (2007)."},{"key":"38913_CR43","unstructured":"Xu, Z., Jain, S. & Kankanhalli, M. \u2018Hallucination is Inevitable: An Innate Limitation of Large Language Models\u2019, arXiv [cs.CL]. (2025)."},{"key":"38913_CR44","doi-asserted-by":"crossref","unstructured":"Xu, J., Szlam, A., Weston, J., Facebook, A. I. & Research Beyond goldfish memory: Long-Term Open-Domain conversation, Jul. (2021).","DOI":"10.18653\/v1\/2022.acl-long.356"},{"key":"38913_CR45","unstructured":"Wei, J. et al. Measuring and reducing LLM hallucination without Gold-Standard answers. ArXiv:2402.10412, 6 June 2024."},{"key":"38913_CR46","unstructured":"Barrett, Heli & Matthews, Jere & Ford, Aino & Castro, Harold & Claire, Imogen& Pum, Mengkorn. (2023). Observability and Monitoring Using Prometheus and Grafana in Cloud Setups"},{"key":"38913_CR47","doi-asserted-by":"crossref","unstructured":"Gar\u00ed, Y., Monge, D. A., Pacini, E., Mateos, C. & Garino, C. G. Reinforcement Learning-based Application Autoscaling in the Cloud: A Survey, arXiv preprint arXiv:.06252, 2020., 2020. (2001).","DOI":"10.1016\/j.engappai.2021.104288"},{"key":"38913_CR48","unstructured":"Schuler, L., Jamil, S. & K\u00fchl, N. AI-based Resource Allocation: Reinforcement Learning for Adaptive Auto-scaling in Serverless Environments, arXiv preprint arXiv:.08595, 2020., 2020. (2005)."},{"issue":"1","key":"38913_CR49","first-page":"1","volume":"9","author":"M Rodrigues","year":"2020","unstructured":"Rodrigues, M., Silva, S. C. G. & Vernet, F. B. A survey on fault tolerance in cloud computing. J. Cloud Comput. 9 (1), 1\u201327 (2020).","journal-title":"J. Cloud Comput."},{"issue":"3","key":"38913_CR50","first-page":"1","volume":"12","author":"M Calic","year":"2023","unstructured":"Calic, M. & Babic, B. Model-based cloud service deployment optimisation method for minimisation of application service operational cost. J. Cloud Comput. 12 (3), 1\u201318 (2023). [Online].","journal-title":"J. Cloud Comput."},{"key":"38913_CR51","doi-asserted-by":"crossref","unstructured":"Tari, M. et al. Auto-Scaling Mechanisms in Serverless Computing: A Comprehensive Review. Computer Science Review, vol. 53, 1 pp. 100650\u2013100650 (2024).","DOI":"10.1016\/j.cosrev.2024.100650"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-38913-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-38913-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-38913-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T17:55:08Z","timestamp":1781632508000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-38913-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,9]]},"references-count":51,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["38913"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-38913-w","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,9]]},"assertion":[{"value":"10 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"The authors declare that this manuscript is theirs, it has not been published or submitted elsewhere and follows ethical standards of publishing. This study did not involve human or animal subjects, and thus no ethical approval was required. All co-authors have consented to the submission and accept responsibility for its content.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"7925"}}