{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T01:23:51Z","timestamp":1787102631973,"version":"build-2736575974"},"reference-count":64,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Data & Knowledge Engineering"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.datak.2026.102627","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T20:04:20Z","timestamp":1783627460000},"page":"102627","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Addressing hallucinations with RAG and NMISS in Italian healthcare LLM chatbots"],"prefix":"10.1016","volume":"165","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4076-0103","authenticated-orcid":false,"given":"Maria Paola","family":"Priola","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.datak.2026.102627_b1","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.datak.2026.102627_b2","series-title":"Introducing ChatGPT","author":"OpenAI","year":"2022"},{"key":"10.1016\/j.datak.2026.102627_b3","series-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b4","series-title":"Chat with Gemini","author":"Google","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b5","series-title":"The RefinedWeb dataset for falcon LLM: Outperforming curated corpora with web data, and web data only","author":"Penedo","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b6","series-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b7","series-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b8","series-title":"Introducing meta LLaMA 3: The most capable openly available LLM to date","author":"Meta AI","year":"2024"},{"key":"10.1016\/j.datak.2026.102627_b9","series-title":"Gemma: Open models based on Gemini research and technology","author":"Gemma Team","year":"2024"},{"key":"10.1016\/j.datak.2026.102627_b10","series-title":"Gemma 2: Improving open language models at a practical size","author":"Gemma Team","year":"2024"},{"key":"10.1016\/j.datak.2026.102627_b11","series-title":"Measuring massive multitask language understanding","author":"Hendrycks","year":"2020"},{"key":"10.1016\/j.datak.2026.102627_b12","article-title":"C-Eval: A multi-level multi-discipline Chinese evaluation suite for foundation models","volume":"36","author":"Huang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.datak.2026.102627_b13","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1162\/tacl_a_00632","article-title":"Benchmarking large language models for news summarization","volume":"12","author":"Zhang","year":"2024","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.datak.2026.102627_b14","series-title":"Simple synthetic data reduces sycophancy in large language models","author":"Wei","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b15","doi-asserted-by":"crossref","first-page":"22199","DOI":"10.52202\/068431-1613","article-title":"Large language models are zero-shot reasoners","volume":"35","author":"Kojima","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.datak.2026.102627_b16","series-title":"Reasoning with language model prompting: A survey","author":"Qiao","year":"2022"},{"key":"10.1016\/j.datak.2026.102627_b17","series-title":"Quick Start Guide to Large Language Models: Strategies and Best Practices for Using ChatGPT and Other LLMs","author":"Ozdemir","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b18","doi-asserted-by":"crossref","first-page":"1500","DOI":"10.1162\/tacl_a_00615","article-title":"Hallucinations in large multilingual translation models","volume":"11","author":"Guerreiro","year":"2023","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.datak.2026.102627_b19","series-title":"A stitch in time saves nine: Detecting and mitigating hallucinations of LLMs by actively validating low-confidence generation","author":"Varshney","year":"2023"},{"issue":"12","key":"10.1016\/j.datak.2026.102627_b20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3571730","article-title":"Survey of hallucination in natural language generation","volume":"55","author":"Ji","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.datak.2026.102627_b21","series-title":"Challenges and applications of large language models","author":"Kaddour","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b22","series-title":"A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions","author":"Huang","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b23","doi-asserted-by":"crossref","first-page":"27730","DOI":"10.52202\/068431-2011","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.datak.2026.102627_b24","series-title":"MOSS: Training conversational language models from synthetic data","author":"Sun","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b25","series-title":"Investigating the factual knowledge boundary of large language models with retrieval augmentation","author":"Ren","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b26","series-title":"Siren\u2019s song in the AI ocean: A survey on hallucination in large language models","author":"Zhang","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b27","series-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","author":"Lewis","year":"2020"},{"key":"10.1016\/j.datak.2026.102627_b28","series-title":"EVER: Mitigating hallucination in large language models through real-time verification and rectification","author":"Kang","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b29","series-title":"A comprehensive survey of hallucination mitigation techniques in large language models","author":"Tonmoy","year":"2024"},{"key":"10.1016\/j.datak.2026.102627_b30","series-title":"A prompt pattern catalog to enhance prompt engineering with ChatGPT","author":"White","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b31","doi-asserted-by":"crossref","first-page":"46534","DOI":"10.52202\/075280-2019","article-title":"Self-refine: Iterative refinement with self-feedback","volume":"36","author":"Madaan","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.datak.2026.102627_b32","series-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","first-page":"3045","article-title":"The power of scale for parameter-efficient prompt tuning","author":"Lester","year":"2021"},{"key":"10.1016\/j.datak.2026.102627_b33","series-title":"Text Summarization Branches Out","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"key":"10.1016\/j.datak.2026.102627_b34","doi-asserted-by":"crossref","unstructured":"K. Papineni, S. Roukos, T. Ward, W.-J. Zhu, BLEU: A Method for Automatic Evaluation of Machine Translation, in: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, 2002, pp. 311\u2013318.","DOI":"10.3115\/1073083.1073135"},{"key":"10.1016\/j.datak.2026.102627_b35","unstructured":"S. Banerjee, A. Lavie, METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments, in: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/Or Summarization, 2005, pp. 65\u201372."},{"key":"10.1016\/j.datak.2026.102627_b36","series-title":"Evaluation of text generation: A survey","author":"Celikyilmaz","year":"2020"},{"key":"10.1016\/j.datak.2026.102627_b37","series-title":"BERTScore: Evaluating text generation with BERT","author":"Zhang","year":"2019"},{"key":"10.1016\/j.datak.2026.102627_b38","series-title":"The internal state of an LLM knows when it\u2019s lying","author":"Azaria","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b39","series-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing","article-title":"Sentence-BERT: Sentence embeddings using siamese BERT-networks","author":"Reimers","year":"2019"},{"key":"10.1016\/j.datak.2026.102627_b40","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing","article-title":"Making monolingual sentence embeddings multilingual using knowledge distillation","author":"Reimers","year":"2020"},{"key":"10.1016\/j.datak.2026.102627_b41","series-title":"Mistral 7B","author":"Jiang","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b42","series-title":"Detecting hallucinations in large language model generation: A token probability approach","author":"Quevedo","year":"2024"},{"key":"10.1016\/j.datak.2026.102627_b43","series-title":"Self-instruct: Aligning language models with self-generated instructions","author":"Wang","year":"2022"},{"key":"10.1016\/j.datak.2026.102627_b44","series-title":"REPLUG: Retrieval-augmented black-box language models","author":"Shi","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b45","series-title":"Verify-and-edit: A knowledge-enhanced chain-of-thought framework","author":"Zhao","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b46","doi-asserted-by":"crossref","unstructured":"L. Jiang, K. Jiang, X. Chu, S. Gulati, P. Garg, Hallucination Detection in LLM-Enriched Product Listings, in: Proceedings of the Seventh Workshop on E-Commerce and NLP@LREC-COLING 2024, 2024, pp. 29\u201339.","DOI":"10.63317\/4r7nnjatdqim"},{"key":"10.1016\/j.datak.2026.102627_b47","series-title":"European Semantic Web Conference","first-page":"182","article-title":"Knowledge injection to counter large language model (LLM) hallucination","author":"Martino","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b48","series-title":"SKILL: Structured knowledge infusion for large language models","author":"Moiseev","year":"2022"},{"key":"10.1016\/j.datak.2026.102627_b49","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2023.104580","article-title":"Retrieval augmentation of large language models for lay language generation","volume":"149","author":"Guo","year":"2024","journal-title":"J. Biomed. Informatics"},{"key":"10.1016\/j.datak.2026.102627_b50","series-title":"Automatic calibration and error correction for large language models via Pareto optimal self-supervision","author":"Zhao","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b51","series-title":"Findings of the Association for Computational Linguistics: ACL 2024","first-page":"2025","article-title":"The knowledge alignment problem: Bridging human and external knowledge for large language models","author":"Zhang","year":"2024"},{"key":"10.1016\/j.datak.2026.102627_b52","series-title":"SelfCheckGPT: Zero-resource black-box hallucination detection for generative large language models","author":"Manakul","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b53","series-title":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","first-page":"245","article-title":"Hallucination detection: Robustly discerning reliable answers in large language models","author":"Chen","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b54","series-title":"BLOOM: A 176b-parameter open-access multilingual language model","author":"Workshop","year":"2022"},{"key":"10.1016\/j.datak.2026.102627_b55","series-title":"Do language models know when they\u2019re hallucinating references?","author":"Agrawal","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b56","series-title":"Self-contradictory hallucinations of large language models: Evaluation, detection and mitigation","author":"M\u00fcndler","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b57","series-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"10.1016\/j.datak.2026.102627_b58","doi-asserted-by":"crossref","unstructured":"S. Es, J. James, L.E. Anke, S. Schockaert, RAGAS: Automated Evaluation of Retrieval-Augmented Generation, in: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, 2024, pp. 150\u2013158.","DOI":"10.18653\/v1\/2024.eacl-demo.16"},{"key":"10.1016\/j.datak.2026.102627_b59","series-title":"Retrieval-augmented generation for large language models: A survey","author":"Gao","year":"2023"},{"key":"10.1016\/j.datak.2026.102627_b60","series-title":"Text Analytics with Python: A Practitioner\u2019s Guide To Natural Language Processing","first-page":"275","article-title":"Text classification","author":"Sarkar","year":"2019"},{"key":"10.1016\/j.datak.2026.102627_b61","series-title":"Introduction to Algorithms","author":"Cormen","year":"2022"},{"issue":"3","key":"10.1016\/j.datak.2026.102627_b62","doi-asserted-by":"crossref","first-page":"862","DOI":"10.1007\/s40593-023-00362-1","article-title":"Text-based question difficulty prediction: A systematic review of automatic approaches","volume":"34","author":"AlKhuzaey","year":"2024","journal-title":"Int. J. Artif. Intell. Educ."},{"key":"10.1016\/j.datak.2026.102627_b63","doi-asserted-by":"crossref","first-page":"46595","DOI":"10.52202\/075280-2020","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","volume":"36","author":"Zheng","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"158","key":"10.1016\/j.datak.2026.102627_b64","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1080\/01621459.1927.10502953","article-title":"Probable inference, the law of succession, and statistical inference","volume":"22","author":"Wilson","year":"1927","journal-title":"J. Amer. Statist. Assoc."}],"container-title":["Data & Knowledge Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0169023X26000741?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0169023X26000741?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T00:26:38Z","timestamp":1787099198000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0169023X26000741"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":64,"alternative-id":["S0169023X26000741"],"URL":"https:\/\/doi.org\/10.1016\/j.datak.2026.102627","relation":{},"ISSN":["0169-023X"],"issn-type":[{"value":"0169-023X","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Addressing hallucinations with RAG and NMISS in Italian healthcare LLM chatbots","name":"articletitle","label":"Article Title"},{"value":"Data & Knowledge Engineering","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.datak.2026.102627","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"102627"}}