{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T03:37:24Z","timestamp":1785469044769,"version":"3.56.0"},"reference-count":85,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100021856","name":"Ministero dell'Universit\u00e0 e della Ricerca","doi-asserted-by":"publisher","award":["20225WTRFN"],"award-info":[{"award-number":["20225WTRFN"]}],"id":[{"id":"10.13039\/501100021856","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002954","name":"Universit\u00e0 degli Studi di Milano - Bicocca","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100002954","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Computing"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>The exponential surge in online health information, coupled with its increasing use by non-experts, highlights the pressing need for advanced Health Information Retrieval (HIR) models that consider not only topical relevance but also the factual accuracy of the retrieved information, given the potential risks associated with health misinformation. To this aim, this paper introduces a solution driven by Retrieval-Augmented Generation (RAG), which leverages the capabilities of generative Large Language Models (LLMs) to enhance the retrieval of health-related documents grounded in scientific evidence. In particular, we propose a three-stage model: in the first stage, the user\u2019s query is employed to retrieve topically relevant passages with associated references from a knowledge base constituted by scientific literature. In the second stage, these passages, alongside the initial query, are processed by LLMs to generate a contextually relevant rich text (GenText). In the last stage, the documents to be retrieved are evaluated and ranked both from the point of view of topical relevance and factual accuracy by means of their comparison with GenText, either through stance detection or semantic similarity. In addition to calculating factual accuracy, GenText can offer a layer of explainability for it, aiding users in understanding the reasoning behind the retrieval. Experimental evaluation of our model on benchmark datasets and against baseline models demonstrates its effectiveness in enhancing the retrieval of both topically relevant and factually accurate health information, thus presenting a significant step forward in the health misinformation mitigation problem.<\/jats:p>","DOI":"10.1007\/s10791-025-09505-5","type":"journal-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T03:39:34Z","timestamp":1743737974000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Enhancing Health Information Retrieval with RAG by prioritizing topical relevance and factual accuracy"],"prefix":"10.1007","volume":"28","author":[{"given":"Rishabh","family":"Upadhyay","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Viviani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,1]]},"reference":[{"key":"9505_CR1","doi-asserted-by":"crossref","unstructured":"Buchanan J, Kock N. Information overload: A decision making perspective. In: Multiple Criteria Decision Making in the New Millennium: Proceedings of the Fifteenth International Conference on Multiple Criteria Decision Making (MCDM) Ankara, Turkey, July 10\u201314, 2001;2000:49\u201358. Springer","DOI":"10.1007\/978-3-642-56680-6_4"},{"key":"9505_CR2","doi-asserted-by":"crossref","unstructured":"Goeuriot L, Suominen H, Kelly L, Alemany LA, Brew-Sam N, Cotik V, Filippo D, Gonzalez\u00a0Saez G, Luque F, Mulhem P, et al. CLEF eHealth Evaluation Lab 2021. In: Advances in Information Retrieval: 43rd European Conference on IR Research, ECIR 2021, Virtual Event, March 28\u2013April 1, 2021, Proceedings, Part II 2021;43:593\u2013600. Springer","DOI":"10.1007\/978-3-030-72240-1_69"},{"key":"9505_CR3","doi-asserted-by":"crossref","unstructured":"Goodrich B, Rao V, Liu PJ, Saleh M. Assessing the factual accuracy of generated text. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019:166\u2013175","DOI":"10.1145\/3292500.3330955"},{"issue":"4","key":"9505_CR4","doi-asserted-by":"crossref","first-page":"2173","DOI":"10.3390\/ijerph19042173","volume":"19","author":"S Di Sotto","year":"2022","unstructured":"Di Sotto S, Viviani M. Health misinformation detection in the social web: an overview and a data science approach. Int J Environ Res Publ Health. 2022;19(4):2173.","journal-title":"Int J Environ Res Publ Health"},{"key":"9505_CR5","doi-asserted-by":"crossref","unstructured":"Abdullah M, Madain A, Jararweh Y. Chatgpt: Fundamentals, applications and social impacts. In: 2022 Ninth International Conference on Social Networks Analysis, Management and Security (SNAMS), 2022:1\u20138. Ieee","DOI":"10.1109\/SNAMS58071.2022.10062688"},{"key":"9505_CR6","unstructured":"Touvron H, Martin L, Stone K, Albert P, Almahairi A, Babaei Y, Bashlykov N, Batra S, Bhargava P, Bhosale S, et al. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 2023"},{"key":"9505_CR7","doi-asserted-by":"crossref","unstructured":"Du Z, Qian Y, Liu X, Ding M, Qiu J, Yang Z, Tang J. Glm: General language model pretraining with autoregressive blank infilling. arXiv preprint arXiv:2103.10360 2021","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"9505_CR8","doi-asserted-by":"crossref","unstructured":"Ackerman R, Balyan R. Automatic multilingual question generation for health data using llms. In: International Conference on AI-generated Content, 2023:1\u201311. Springer","DOI":"10.1007\/978-981-99-7587-7_1"},{"key":"9505_CR9","doi-asserted-by":"crossref","unstructured":"Frisoni G, Cocchieri A, Presepi A, Moro G, Meng Z. To generate or to retrieve? on the effectiveness of artificial contexts for medical open-domain question answering. arXiv preprint arXiv:2403.01924 2024.","DOI":"10.18653\/v1\/2024.acl-long.533"},{"key":"9505_CR10","doi-asserted-by":"crossref","unstructured":"Kell G, Roberts A, Umansky S, Qian L, Ferrari D, Soboczenski F, Wallace B, Patel N, Marshall IJ. Question answering systems for health professionals at the point of care\u2013a systematic review. arXiv preprint arXiv:2402.01700 2024.","DOI":"10.1093\/jamia\/ocae015"},{"key":"9505_CR11","doi-asserted-by":"crossref","unstructured":"Bang Y, Cahyawijaya S, Lee N, Dai W, Su D, Wilie B, Lovenia H, Ji Z, Yu T, Chung W, et al. A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity. arXiv preprint arXiv:2302.04023 2023.","DOI":"10.18653\/v1\/2023.ijcnlp-main.45"},{"key":"9505_CR12","unstructured":"Guo B, Zhang X, Wang Z, Jiang M, Nie J, Ding Y, Yue J, Wu Y. How close is chatgpt to human experts? comparison corpus, evaluation, and detection. arXiv preprint arXiv:2301.07597 2023."},{"key":"9505_CR13","doi-asserted-by":"crossref","unstructured":"Cao M, Dong Y, Wu J, Cheung JCK. Factual error correction for abstractive summarization models. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 6251\u20136258. Association for Computational Linguistics, Online 2020.","DOI":"10.18653\/v1\/2020.emnlp-main.506"},{"key":"9505_CR14","doi-asserted-by":"crossref","unstructured":"Raunak V, Menezes A, Junczys-Dowmunt M. The curious case of hallucinations in neural machine translation. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1172\u20131183. Association for Computational Linguistics, Online 2021.","DOI":"10.18653\/v1\/2021.naacl-main.92"},{"issue":"12","key":"9505_CR15","first-page":"10","volume":"55","author":"Z Ji","year":"2023","unstructured":"Ji Z, Lee N, Frieske R, Yu T, Su D, Xu Y, Ishii E, Bang YJ, Madotto A, Fung P. Survey of hallucination in natural language generation. ACM Comput Surv. 2023;55(12):10.","journal-title":"ACM Comput Surv"},{"key":"9505_CR16","unstructured":"Saxena S, Prasad S, Prakash M, Shankar A, Vaddina V, Gopalakrishnan S, et al. Minimizing factual inconsistency and hallucination in large language models. arXiv preprint arXiv:2311.13878 2023."},{"key":"9505_CR17","unstructured":"Huang L, Yu W, Ma W, Zhong W, Feng Z, Wang H, Chen Q, Peng W, Feng X, Qin B, et al. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. arXiv preprint arXiv:2311.05232 2023."},{"key":"9505_CR18","unstructured":"Zhang Y, Li Y, Cui L, Cai D, Liu L, Fu T, Huang X, Zhao E, Zhang Y, Chen Y, et al. Siren\u2019s song in the ai ocean: a survey on hallucination in large language models. arXiv preprint arXiv:2309.01219 2023."},{"key":"9505_CR19","unstructured":"He H, Zhang H, Roth D. Rethinking with retrieval: Faithful large language model inference. arXiv preprint arXiv:2301.00303 2022."},{"key":"9505_CR20","doi-asserted-by":"crossref","unstructured":"Li X, Zhu X, Ma Z, Liu X, Shah S. Are chatgpt and gpt-4 general-purpose solvers for financial text analytics? an examination on several typical tasks. arXiv preprint arXiv:2305.05862 2023.","DOI":"10.18653\/v1\/2023.emnlp-industry.39"},{"key":"9505_CR21","unstructured":"Shen X, Chen Z, Backes M, Zhang Y. In chatgpt we trust? measuring and characterizing the reliability of chatgpt. arXiv preprint arXiv:2304.08979 2023."},{"key":"9505_CR22","first-page":"9459","volume":"33","author":"P Lewis","year":"2020","unstructured":"Lewis P, Perez E, Piktus A, Petroni F, Karpukhin V, Goyal N, K\u00fcttler H, Lewis M, Yih W-T, Rockt\u00e4schel T, et al. Retrieval-augmented generation for knowledge-intensive nlp tasks. Adv Neural Inform Process Syst. 2020;33:9459\u201374.","journal-title":"Adv Neural Inform Process Syst"},{"key":"9505_CR23","doi-asserted-by":"crossref","unstructured":"Perkovi\u0107 G, Drobnjak A, Boti\u010dki I. Hallucinations in llms: Understanding and addressing challenges. In: 2024 47th MIPRO ICT and Electronics Convention (MIPRO), 2024: 2084\u20132088. IEEE.","DOI":"10.1109\/MIPRO60963.2024.10569238"},{"key":"9505_CR24","unstructured":"Borgeaud S, Mensch A, Hoffmann J, Cai T, Rutherford E, Millican K, Van Den\u00a0Driessche GB, Lespiau J-B, Damoc B, Clark A, et al. Improving language models by retrieving from trillions of tokens. In: International Conference on Machine Learning, 2022:2206\u20132240. PMLR."},{"key":"9505_CR25","unstructured":"Guu K, Lee K, Tung Z, Pasupat P, Chang M. Retrieval augmented language model pre-training. In: International Conference on Machine Learning, 2020:3929\u20133938. PMLR."},{"issue":"251","key":"9505_CR26","first-page":"1","volume":"24","author":"G Izacard","year":"2023","unstructured":"Izacard G, Lewis P, Lomeli M, Hosseini L, Petroni F, Schick T, Dwivedi-Yu J, Joulin A, Riedel S, Grave E. Atlas: few-shot learning with retrieval augmented language models. J Machine Learn Res. 2023;24(251):1\u201343.","journal-title":"J Machine Learn Res"},{"key":"9505_CR27","unstructured":"Setty S, Jijo K, Chung E, Vidra N. Improving retrieval for rag based question answering models on financial documents. arXiv preprint arXiv:2404.07221 2024."},{"key":"9505_CR28","doi-asserted-by":"crossref","unstructured":"Kang C, Novak D, Urbanova K, Cheng Y, Hu Y. Domain-specific improvement on psychotherapy chatbot using assistant. arXiv preprint arXiv:2404.16160 2024.","DOI":"10.2139\/ssrn.4616282"},{"key":"9505_CR29","doi-asserted-by":"crossref","unstructured":"Adlakha V, BehnamGhader P, Lu XH, Meade N, Reddy S. Evaluating correctness and faithfulness of instruction-following models for question answering. arXiv preprint arXiv:2307.16877 2023.","DOI":"10.1162\/tacl_a_00667"},{"key":"9505_CR30","doi-asserted-by":"crossref","unstructured":"Clarke CL, Maistro M, Smucker MD, Zuccon G. Overview of the trec 2020 health misinformation track. In: TREC 2020.","DOI":"10.6028\/NIST.SP.1266.misinfo-overview"},{"key":"9505_CR31","doi-asserted-by":"crossref","unstructured":"Zhao R, Arana-Catania M, Zhu L, Kochkina E, Gui L, Zubiaga A, Procter R, Liakata M, He Y. Panacea: An automated misinformation detection system on covid-19. arXiv preprint arXiv:2303.01241 2023.","DOI":"10.18653\/v1\/2023.eacl-demo.9"},{"key":"9505_CR32","doi-asserted-by":"crossref","unstructured":"Mendes E, Chen Y, Xu W, Ritter A. Human-in-the-loop evaluation for early misinformation detection: A case study of covid-19 treatments. arXiv preprint arXiv:2212.09683 2022.","DOI":"10.18653\/v1\/2023.acl-long.881"},{"key":"9505_CR33","doi-asserted-by":"crossref","unstructured":"Yue Z, Zeng H, Kou Z, Shang L, Wang D. Contrastive domain adaptation for early misinformation detection: A case study on covid-19. In: Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022:2423\u20132433.","DOI":"10.1145\/3511808.3557263"},{"issue":"5","key":"9505_CR34","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2022.103029","volume":"59","author":"G Jiang","year":"2022","unstructured":"Jiang G, Liu S, Zhao Y, Sun Y, Zhang M. Fake news detection via knowledgeable prompt learning. Inform Process Management. 2022;59(5): 103029.","journal-title":"Inform Process Management"},{"key":"9505_CR35","unstructured":"Chen C, Shu K. Can llm-generated misinformation be detected? arXiv preprint arXiv:2309.13788 2023."},{"issue":"4","key":"9505_CR36","doi-asserted-by":"crossref","first-page":"5271","DOI":"10.1007\/s11042-022-13368-z","volume":"82","author":"R Upadhyay","year":"2023","unstructured":"Upadhyay R, Pasi G, Viviani M. Vec4cred: a model for health misinformation detection in web pages. Multimedia Tools Appl. 2023;82(4):5271\u201390.","journal-title":"Multimedia Tools Appl"},{"key":"9505_CR37","doi-asserted-by":"crossref","unstructured":"Upadhyay R, Pasi G, Viviani M. Health misinformation detection in web content: A structural-, content-based, and context-aware approach based on web2vec. In: Proceedings of the Conference on Information Technology for Social Good. GoodIT \u201921, pp. 19\u201324. Association for Computing Machinery, New York, NY, USA 2021.","DOI":"10.1145\/3462203.3475898"},{"key":"9505_CR38","doi-asserted-by":"crossref","unstructured":"Upadhyay R, Pasi G, Viviani M. Leveraging socio-contextual information in bert for fake health news detection in social media. In: Proceedings of the 3rd International Workshop on Open Challenges in Online Social Networks. OASIS \u201923, pp. 38\u201346. Association for Computing Machinery, New York, NY, USA 2023.","DOI":"10.1145\/3599696.3612902"},{"key":"9505_CR39","unstructured":"Brand E, Roitero K, Soprano M, Demartini G, et al. E-bart: Jointly predicting and explaining truthfulness. In: Proceedings of the Conference for Truth and Trust Online 2021."},{"key":"9505_CR40","doi-asserted-by":"crossref","unstructured":"Kou Z, Shang L, Zhang Y, Wang D. Hc-covid: A hierarchical crowdsource knowledge graph approach to explainable covid-19 misinformation detection. Proceedings of the ACM on Human-Computer Interaction 6(GROUP), 2022:1\u201325","DOI":"10.1145\/3492855"},{"key":"9505_CR41","doi-asserted-by":"crossref","unstructured":"Wu J, Liu Q, Xu W, Wu S. Bias mitigation for evidence-aware fake news detection by causal intervention. In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2022:2308\u20132313","DOI":"10.1145\/3477495.3531850"},{"key":"9505_CR42","doi-asserted-by":"crossref","first-page":"1184851","DOI":"10.3389\/frai.2023.1184851","volume":"6","author":"R Upadhyay","year":"2023","unstructured":"Upadhyay R, Knoth P, Pasi G, Viviani M. Explainable online health information truthfulness in consumer health search. Front Artif Intell. 2023;6:1184851.","journal-title":"Front Artif Intell"},{"key":"9505_CR43","doi-asserted-by":"crossref","unstructured":"Shang L, Zhang Y, Yue Z, Choi Y, Zeng H, Wang D. A knowledge-driven domain adaptive approach to early misinformation detection in an emergent health domain on social media. In: 2022 IEEE\/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), 2022: 34\u201341. IEEE","DOI":"10.1109\/ASONAM55673.2022.10068587"},{"key":"9505_CR44","doi-asserted-by":"crossref","unstructured":"Hassan N, Arslan F, Li C, Tremayne M. Toward automated fact-checking: Detecting check-worthy factual claims by claimbuster. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2017:1803\u20131812","DOI":"10.1145\/3097983.3098131"},{"key":"9505_CR45","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1162\/tacl_a_00454","volume":"10","author":"Z Guo","year":"2022","unstructured":"Guo Z, Schlichtkrull M, Vlachos A. A survey on automated fact-checking. Trans Assoc Computational Linguistics. 2022;10:178\u2013206.","journal-title":"Trans Assoc Computational Linguistics"},{"key":"9505_CR46","doi-asserted-by":"crossref","unstructured":"Zeng X, La\u00a0Barbera D, Roitero K, Zubiaga A, Mizzaro S. Combining large language models and crowdsourcing for hybrid human-ai misinformation detection. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2024:2332\u20132336","DOI":"10.1145\/3626772.3657965"},{"key":"9505_CR47","unstructured":"Goeuriot L, Suominen H, Pasi G, Bassani E, Brew-Sam N, Gonz\u00e1lez-S\u00e1ez G, Kelly L, Mulhem P, Seneviratne S, Upadhyay R, et al. Consumer health search at clef ehealth 2021. In: CEUR Workshop Proceedings, 2021:1\u201319. CEUR"},{"key":"9505_CR48","unstructured":"Di\u00a0Nunzio GM, Marchesin S, Vezzani F. A Study on Reciprocal Ranking Fusion in Consumer Health Search. IMS UniPD ad CLEF eHealth 2020 Task 2. In: CLEF (Working Notes) 2020."},{"key":"9505_CR49","doi-asserted-by":"crossref","unstructured":"Cormack GV, Clarke CL, Buettcher S. Reciprocal rank fusion outperforms condorcet and individual rank learning methods. In: Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2009:758\u2013759","DOI":"10.1145\/1571941.1572114"},{"key":"9505_CR50","unstructured":"Mulhem P, Saez GG, Mannion A, Schwab D, Frej J. Lig-health at adhoc and spoken ir consumer health search: expanding queries using umls and fasttext. In: CLEF 2020."},{"key":"9505_CR51","unstructured":"Seneviratne S, Daskalaki E, Hossain MZ, Lenskiy A. Sandidoc at clef 2020-consumer health search: Adhoc ir task. In: CLEF (Working Notes) 2020."},{"key":"9505_CR52","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez-Pichel M, Losada DE, Pichel JC, Elsweiler D. Citius at the trec 2020 health misinformation track. In: TREC 2020.","DOI":"10.6028\/NIST.SP.1266.misinfo-CiTIUS"},{"key":"9505_CR53","doi-asserted-by":"crossref","unstructured":"Zhang B, Naderi N, Jaume-Santero F, Teodoro D. Ds4dh at trec health misinformation 2021: multi-dimensional ranking models with transfer learning and rank fusion. arXiv preprint arXiv:2202.06771 2022.","DOI":"10.6028\/NIST.SP.500-335.misinfo-DigiLab"},{"key":"9505_CR54","unstructured":"Schlicht IB, Paula AFM, Rosso P. Upv at trec health misinformation track 2021 ranking with sbert and quality estimators. arXiv preprint arXiv:2112.06080 2021."},{"key":"9505_CR55","doi-asserted-by":"crossref","unstructured":"Abualsaud M, Chen IX, Ghajar K, Minh L, Smucker M, Tahami AV, Zhang D. Uwaterloomds at the trec 2021 health misinformation track. In: Proceedings of the Thirtieth REtrieval Conference Proceedings (TREC 2021). National Institute of Standards and Technology (NIST), Special Publication, 2021:1\u201318","DOI":"10.6028\/NIST.SP.500-335.misinfo-UWaterlooMDS"},{"key":"9505_CR56","unstructured":"Pankaj S, Gautam A. Augmented bio-sbert: Improving performance for pairwise sentence tasks in bio-medical domain. In: Proceedings of the Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2022), 2022:43\u201347"},{"issue":"140","key":"9505_CR57","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou Y, Li W, Liu PJ. Exploring the limits of transfer learning with a unified text-to-text transformer. J Machine Learn Res. 2020;21(140):1\u201367.","journal-title":"J Machine Learn Res"},{"key":"9505_CR58","doi-asserted-by":"crossref","unstructured":"Wan H, Feng S, Tan Z, Wang H, Tsvetkov Y, Luo M. Dell: Generating reactions and explanations for llm-based misinformation detection. arXiv preprint arXiv:2402.10426 2024.","DOI":"10.18653\/v1\/2024.findings-acl.155"},{"key":"9505_CR59","first-page":"1441","volume":"2024","author":"EC Choi","year":"2024","unstructured":"Choi EC, Ferrara E. Automated claim matching with large language models: empowering fact-checkers in the fight against misinformation. Companion Proc ACM Web Conf. 2024;2024:1441\u20139.","journal-title":"Companion Proc ACM Web Conf"},{"key":"9505_CR60","unstructured":"Cao Y, Nair AM, Eyimife E, Soofi NJ, Subbalakshmi K, Wullert\u00a0II JR, Basu C, Shallcross D. Can large language models detect misinformation in scientific news reporting? arXiv preprint arXiv:2402.14268 2024."},{"key":"9505_CR61","unstructured":"Wang J, Yang Z, Yao Z, Yu H. Jmlr: Joint medical llm and retrieval training for enhancing reasoning and professional question answering capability. arXiv preprint arXiv:2402.17887 2024."},{"key":"9505_CR62","doi-asserted-by":"crossref","unstructured":"Khlaut J, Dancette C, Ferreres E, Bennani A, H\u00e9rent P, Manceron P. Efficient medical question answering with knowledge-augmented question generation. arXiv preprint arXiv:2405.14654 2024.","DOI":"10.18653\/v1\/2024.clinicalnlp-1.2"},{"key":"9505_CR63","doi-asserted-by":"crossref","unstructured":"Shi W, Min S, Yasunaga M, Seo M, James R, Lewis M, Zettlemoyer L, Yih W-t. Replug: Retrieval-augmented black-box language models. arXiv preprint arXiv:2301.12652 2023.","DOI":"10.18653\/v1\/2024.naacl-long.463"},{"key":"9505_CR64","unstructured":"Ren R, Wang Y, Qu Y, Zhao WX, Liu J, Tian H, Wu H, Wen J-R, Wang H. Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation 2023."},{"key":"9505_CR65","doi-asserted-by":"crossref","unstructured":"Izacard G, Grave E. Leveraging passage retrieval with generative models for open domain question answering. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 874\u2013880. Association for Computational Linguistics, Online 2021.","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"9505_CR66","doi-asserted-by":"crossref","unstructured":"Trivedi H, Balasubramanian N, Khot T, Sabharwal A. Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 10014\u201310037. Association for Computational Linguistics, Toronto, Canada 2023.","DOI":"10.18653\/v1\/2023.acl-long.557"},{"key":"9505_CR67","doi-asserted-by":"crossref","unstructured":"Li D, Rawat AS, Zaheer M, Wang X, Lukasik M, Veit A, Yu F, Kumar S. Large language models with controllable working memory. In: Findings of the Association for Computational Linguistics: ACL 2023, pp. 1774\u20131793. Association for Computational Linguistics, Toronto, Canada 2023.","DOI":"10.18653\/v1\/2023.findings-acl.112"},{"key":"9505_CR68","doi-asserted-by":"crossref","unstructured":"Cai D, Wang Y, Bi W, Tu Z, Liu X, Lam W, Shi S. Skeleton-to-response: Dialogue generation guided by retrieval memory. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 1219\u20131228. Association for Computational Linguistics, Minneapolis, Minnesota 2019.","DOI":"10.18653\/v1\/N19-1124"},{"key":"9505_CR69","doi-asserted-by":"crossref","unstructured":"Cai D, Wang Y, Bi W, Tu Z, Liu X, Shi S. Retrieval-guided dialogue response generation via a matching-to-generation framework. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 1866\u20131875. Association for Computational Linguistics, Hong Kong, China 2019.","DOI":"10.18653\/v1\/D19-1195"},{"key":"9505_CR70","unstructured":"Peng B, Galley M, He P, Cheng H, Xie Y, Hu Y, Huang Q, Liden L, Yu Z, Chen W, et al. Check your facts and try again: Improving large language models with external knowledge and automated feedback. arXiv preprint arXiv:2302.12813 2023."},{"key":"9505_CR71","unstructured":"Cui J, Li Z, Yan Y, Chen B, Yuan L. Chatlaw: Open-source legal large language model with integrated external knowledge bases. arXiv preprint arXiv:2306.16092 2023."},{"key":"9505_CR72","unstructured":"Zhou S, Alon U, Xu FF, Jiang Z, Neubig G. Docprompting: Generating code by retrieving the docs. In: The Eleventh International Conference on Learning Representations 2023."},{"key":"9505_CR73","unstructured":"Chern I, Chern S, Chen S, Yuan W, Feng K, Zhou C, He J, Neubig G, Liu P, et al. Factool: Factuality detection in generative ai\u2013a tool augmented framework for multi-task and multi-domain scenarios. arXiv preprint arXiv:2307.13528 2023."},{"key":"9505_CR74","doi-asserted-by":"crossref","unstructured":"Pan L, Wu X, Lu X, Luu AT, Wang WY, Kan M-Y, Nakov P. Fact-checking complex claims with program-guided reasoning. arXiv preprint arXiv:2305.12744 2023.","DOI":"10.18653\/v1\/2023.acl-long.386"},{"key":"9505_CR75","doi-asserted-by":"crossref","unstructured":"Zhang X, Gao W. Towards llm-based fact verification on news claims with a hierarchical step-by-step prompting method. arXiv preprint arXiv:2310.00305 2023.","DOI":"10.18653\/v1\/2023.ijcnlp-main.64"},{"key":"9505_CR76","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1162\/tacl_a_00649","volume":"12","author":"F Zeng","year":"2024","unstructured":"Zeng F, Gao W. Justilm: Few-shot justification generation for explainable fact-checking of real-world claims. Trans Assoc Comput Linguist. 2024;12:334\u201354.","journal-title":"Trans Assoc Comput Linguist"},{"issue":"4","key":"9505_CR77","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1561\/1500000019","volume":"3","author":"S Robertson","year":"2009","unstructured":"Robertson S, Zaragoza H, et al. The probabilistic relevance framework and beyond. Foundations Trends Inform Retrieval. 2009;3(4):333\u201389.","journal-title":"Foundations Trends Inform Retrieval"},{"key":"9505_CR78","doi-asserted-by":"crossref","unstructured":"Upadhyay R, Pasi G, Viviani M. A passage retrieval transformer-based re-ranking model for truthful consumer health search. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 2023:355\u2013371. Springer","DOI":"10.1007\/978-3-031-43412-9_21"},{"issue":"4","key":"9505_CR79","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee J, Yoon W, Kim S, Kim D, Kim S, So CH, Kang J. Biobert: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics. 2020;36(4):1234\u201340.","journal-title":"Bioinformatics"},{"key":"9505_CR80","doi-asserted-by":"crossref","unstructured":"Izacard G, Grave E. Leveraging passage retrieval with generative models for open domain question answering. arXiv preprint arXiv:2007.01282 2020.","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"9505_CR81","unstructured":"Phan LN, Anibal JT, Tran H, Chanana S, Bahadroglu E, Peltekian A, Altan-Bonnet G. Scifive: a text-to-text transformer model for biomedical literature. arXiv preprint arXiv:2106.03598 2021."},{"key":"9505_CR82","unstructured":"Bajaj P, Campos D, Craswell N, Deng L, Gao J, Liu X, Majumder R, McNamara A, Mitra B, Nguyen T, et al. MS MARCO: A human generated machine reading comprehension dataset. arXiv preprint arXiv:1611.09268 2016."},{"key":"9505_CR83","doi-asserted-by":"crossref","unstructured":"Schwarz J, Morris M. Augmenting web pages and search results to support credibility assessment. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 2011:1245\u20131254","DOI":"10.1145\/1978942.1979127"},{"key":"9505_CR84","doi-asserted-by":"crossref","unstructured":"Upadhyay R, Pasi G, Viviani M. An unsupervised approach to genuine health information retrieval based on scientific evidence. In: International Conference on Web Information Systems Engineering, 2022:119\u2013135. Springer","DOI":"10.1007\/978-3-031-20891-1_10"},{"key":"9505_CR85","doi-asserted-by":"crossref","unstructured":"Lioma C, Simonsen JG, Larsen B. Evaluation measures for relevance and credibility in ranked lists. In: Proceedings of the ACM SIGIR International Conference on Theory of Information Retrieval, 2017:91\u201398","DOI":"10.1145\/3121050.3121072"}],"container-title":["Discover Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-025-09505-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10791-025-09505-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-025-09505-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T03:41:07Z","timestamp":1743738067000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10791-025-09505-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,1]]},"references-count":85,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["9505"],"URL":"https:\/\/doi.org\/10.1007\/s10791-025-09505-5","relation":{},"ISSN":["2948-2992"],"issn-type":[{"value":"2948-2992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,1]]},"assertion":[{"value":"23 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors declare they have no financial interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"27"}}