Retrieval-Augmented Generation (RAG) in Healthcare: A Comprehensive Review
Open accessPublished version of a preprint
The DOI matches its Crossref record; 80 of the 81 references it cites were found in a registry or an index, and 1 are not checked yet; 24 of the 47 sources its claims cite were checked for support.
Abstract
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieval to improve factual consistency and reduce hallucinations. Despite growing interest, its use in healthcare remains fragmented. This paper presents a Systematic Literature Review (SLR) following PRISMA guidelines, synthesizing 30 peer-reviewed studies on RAG in clinical domains, focusing on three of its most prevalent and promising applications in diagnostic support, electronic health record (EHR) summarization, and medical question answering. Persistent challenges are identified, including retrieval noise, domain shift, generation latency, and limited explainability.
Verified 2026-11-22 · 1 reference not checked yet
Overview
CoChat Summary
TL;DR
This systematic review synthesizes 30 peer-reviewed studies on retrieval-augmented generation (RAG) in healthcare, focusing on diagnostic support, EHR summarization, and medical question answering. It argues that RAG improves factual grounding and interpretability, but healthcare deployment is still limited by retrieval noise, latency, explainability, privacy, and drift.
Key findings
- The review synthesized 30 peer-reviewed studies and organized them into healthcare use cases including diagnostic support, EHR summarization, medical question answering, chatbots, and specialty-specific systems.
- It identifies persistent challenges in healthcare RAG as retrieval noise, domain shift, generation latency, and limited explainability; later sections also add privacy, multimodal limitations, infrastructure constraints, knowledge drift, bias/fairness, and lack of human oversight.
- The paper highlights clinical evaluation metrics that are more suitable than generic NLP metrics, naming FactScore, RadGraph-F1, and MED-F1 as especially important for factual accuracy, medical validity, and clinical relevance.
- The authors conclude that Advanced RAG appears “most ready for pilot clinical use,” while Modular RAG has long-term potential but is harder to deploy because of higher complexity and computational cost.
Methods
- Systematic literature review following PRISMA 2020 guidelines, prospectively registered in OSF.
- Searched PubMed, IEEE Xplore, Scopus, Web of Science, Google Scholar, and ACM Digital Library for publications from 2022 to 2025 using RAG/healthcare/LLM-related search terms.
- Screening flow: 123 records identified, 46 duplicates removed, 77 screened by title/abstract, 47 excluded, and 30 full-text studies included.
- Studies were classified using a taxonomy of RAG applications and compared across architectural variants, applications, metrics, and challenges.
Limitations
- The paper states that the evolving terminology around RAG may have led to exclusion of some studies.
- It states the review relied solely on reported findings rather than raw experimental data and was constrained by a narrow publication window, which may limit completeness and generalizability.
- Evident from the text: the synthesis depends on English-language, peer-reviewed or high-quality preprint sources only, which the paper itself identifies as a source of selection bias.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
20 Valid · 25 Not valid · 23 Not checked · 119 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“However, these models required structured inputs and extensive manual feature engineering to extract meaningful signals from clinical text [13].”
What the sources say
- Partly supportedcites [13] 13. Spasic, I.; Nenadic, G. Clinical text data in machine learning: Systematic review. JMIR Med. Inform. 2020 , 8 , e17984. [CrossRef] sourceExperimental — accuracy not yet measured
The Results (Availability; page not provided) say that most reviewed studies relied on manual annotation of clinical text, and the Discussion identifies annotation as a key bottleneck. Manual annotation is not the same as manual feature engineering, however, and the review does not say that machine-learning models required structured inputs. (LLM, conf=0.83)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Introduced in 2020, Retrieval-Augmented Generation (RAG) mitigates these limitations by combining a retriever which accesses external sources such as clinical guidelines or EHRs with a generator that conditions responses on both the query and retrieved content [8].”
What the sources say
- Partly supportedcites [8] 8. Lewis, P.; Perez, E.; Piktus, A.; Petroni, F.; Karpukhin, V.; Goyal, N.; Küttler, H.; Lewis, M.; Yih, W.T.; Rocktäschel, T.; et al. Retrieval-augmented generation for knowledge-intensive nlp tasks. Adv. Neural Inf. Process. Syst. 2020 , 33 , 9459-9474. sourceExperimental — accuracy not yet measured
The Introduction (p. 2) and Methods (p. 2) describe a retriever that obtains documents and a generator conditioned on both the input and those documents; the Discussion (p. 9) reports benefits over a purely parametric model. The paper’s experiments use Wikipedia as the knowledge source (Experiments, p. 4), not clinical guidelines or EHRs, so the cited paper does not support those examples. (LLM, conf=0.86)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“While interest in RAG continues to grow, most prior work has focused either on architectural innovations [10] or on isolated components such as retriever and generator design [11].”
What the sources say
- Partly supportedcites [10] 10. Gao, Y.; Xiong, Y.; Gao, X.; Jia, K.; Pan, J.; Bi, Y.; Dai, Y.; Sun, J.; Wang, H.; Wang, H. Retrieval-augmented generation for large language models: A survey. arXiv 2023 , arXiv:2312.10997. sourceExperimental — accuracy not yet measured
The Introduction describes Retrieval and Generation as core components studied in the survey, and the Modular RAG section gives examples of refining retrievers and fine-tuning generators. But the paper also discusses interactions between modules; these passages do not establish that most prior work studied the components in isolation. The architectural-innovations clause is attached to a different citation and is not judged here. (LLM, conf=0.82)
- Partly supportedcites [11] 11. Zhao, P.; Zhang, H.; Yu, Q.; Wang, Z.; Geng, Y.; Fu, F.; Yang, L.; Zhang, W.; Jiang, J.; Cui, B. Retrieval-Augmented Generation for AI-Generated Content: A Survey. arXiv 2024 , arXiv:2402.19473. sourceExperimental — accuracy not yet measured
The Background (p. 1) says prior RAG enhancements include optimizations of individual components, and the Preliminary section (p. 3) discusses retrievers and generators. But the Background also describes holistic pipeline enhancements; the paper does not establish that most prior work focused on isolated components. The architectural-innovations clause is attached to a different citation and is not assessed here. (LLM, conf=0.84)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“medical domain-specific LLMs such as Medical Pathways Language Model (Med-PaLM) [2] and Biomedical Generative Pretrained Transformer (BioGPT) [3] have shown improved performance across various clinical natural language processing (NLP) tasks, including question answering, summarization, entity recognition, relation extraction, document classification, and literature mining.”
What the sources say
- Partly supportedcites [2] 2. Singhal, K.; Tu, T.; Gottweis, J.; Sayres, R.; Wulczyn, E.; Amin, M.; Hou, L.; Clark, K.; Pfohl, S.R.; Cole-Lewis, H.; et al. Toward expert-level medical question answering with large language models. Nat. Med. 2025 , 31 , 943-950. [CrossRef] [PubMed] sourceExperimental — accuracy not yet measured
The Abstract (page unavailable) reports improved Med-PaLM 2 performance on medical question-answering benchmarks, supporting the question-answering part of the claim. The cited paper does not establish improved Med-PaLM performance on the other listed tasks—summarization, entity recognition, relation extraction, document classification, or literature mining. BioGPT has a separate citation in the citing sentence and is not assessed here. (LLM, conf=0.86)
- Partly supportedcites [3] 3. Luo, R.; Sun, L.; Xia, Y.; Qin, T.; Zhang, S.; Poon, H.; Liu, T.Y. BioGPT: generative pre-trained transformer for biomedical text generation and mining. Briefings Bioinform. 2022 , 23 , bbac409. [CrossRef] [PubMed] sourceExperimental — accuracy not yet measured
The Introduction (p. 1) identifies BioGPT as a domain-specific model and reports better performance on biomedical question answering, relation extraction, document classification, and text generation. The Experiments section (p. 4) lists those evaluated tasks, but not summarization or entity recognition; its biomedical-literature evaluations also do not establish improved performance across clinical NLP tasks generally. This verdict concerns BioGPT, not Med-PaLM, which has a separate citation. (LLM, conf=0.88)
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Variants of Bidirectional Encoder Representations from Transformers (BERT) [5], such as Biomedical BERT (BioBERT) [6] and ClinicalBERT [7], improve the contextual understanding of medical terminology.”
What the sources say
- Not checked — no full text of the sourcecites [5] 5. Devlin, J.; Chang, M.W.; Lee, K.; Toutanova, K. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, MN, USA, 2-7 June 2019; Volume 1, pp. 4171-4186. source
- Supportedcites [6] 6. Lee, J.; Yoon, W.; Kim, S.; Kim, D.; Kim, S.; So, C.H.; Kang, J. BioBERT: A pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 2020 , 36 , 1234-1240. [CrossRef] source
The Introduction describes BioBERT as an adaptation of BERT to biomedical language, where specialized terms make general-domain models less effective. The Conclusion reports that BioBERT outperforms previous models on biomedical text-mining tasks. Citation [6] is attached to BioBERT; the separate ClinicalBERT citation [7] is not a claim this source needs to support. (LLM, conf=0.90)
- Supportedcites [7] 7. Huang, K.; Altosaar, J.; Ranganath, R. ClinicalBert: Modeling Clinical Notes and Predicting Hospital Readmission. arXiv 2019 , arXiv:1904.05342. source
Our copy identifies ClinicalBERT as a BERT variant specialized to clinical notes ('ClinicalBERT is bert [11] specialized to clinical notes', 1.2 Significance, p. 2; Abstract, p. 1) and shows it improves contextual understanding of clinical/medical terminology: it outperforms bert on clinical language modeling (Table 1, p. 3), and its contextual embeddings correlate with physician-rated similarity of medical concepts (0.670 vs 0.553 Word2Vec and 0.487 FastText, Table 2, p. 4; §3.2.2, p. 4 'ClinicalBERT captures some clinical semantics'). The Background (p. 1) also motivates contextual BERT representations as needed to capture clinical meaning that local-context models miss. BioBERT itself is not discussed in this paper, but that element of the sentence carries its own separate citation ([6]), so it is not part of what is attributed here. (LLM, conf=0.85)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
36 more claims · 2 with their cited sources checked
Create a free account to see all 187 claims and to verify the 13 references still open.
- It may state two separate claims as one. 85
- Probably not a substantial claim. 119
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“RAG-based knowledge grounding in all three agents reduces hallucination rates and supports factual reliability claims that would be required in device submissions (Neha et al., 2025).”
From A generative AI multi-agent framework with integrated XAI governance for cancer diagnostics: from multi-omics interpretation to lifestyle risk stratification (2026) · cites this paper as Neha et al., 2025
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The LLM component, grounded in clinical epidemiology databases through RAG, provides causal annotation for each SHAP-ranked factor, distinguishing established causal risk factors from confounded associations and calibrating recommendation strength accordingly (Neha et al., 2025).”
From A generative AI multi-agent framework with integrated XAI governance for cancer diagnostics: from multi-omics interpretation to lifestyle risk stratification (2026) · cites this paper as Neha et al., 2025
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“It has been observed that LLMs are effective zero-shot or one-shot clinical information extractors.6”
From A Scalable Method for Validated Data Extraction from Electronic Health Records with Large Language Models (2025) · cites this paper as [6]
Experimental — accuracy not yet measured
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · 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) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
BioBERT: a pre-trained biomedical language representation model for biomedical text mining
Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C. H., & Kang, J. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btz682 · Cited by 7,218 · cited 1×
“Variants of Bidirectional Encoder Representations from Transformers (BERT) [5], such as Biomedical BERT (BioBERT) [6] and ClinicalBERT [7], improve the contextual understanding of medical terminology.”
Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network
Sherstinsky, A. (2020) · Physica D: Nonlinear Phenomena · doi:10.1016/j.physd.2019.132306 · Cited by 5,680 · cited 1×
“Deep learning further advanced the field by enabling end-to-end processing of unstructured data, with early implementations using recurrent neural networks (RNNs) and Long Short-Term Memory (LSTM) networks [14].”
Dense passage retrieval for open-domain question answering
Karpukhin, V., Oguz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., & Yih, W.-T. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.550 · Cited by 3,575 · cited 1×
“Popular dense retrievers include dense passage retrieval (DPR) [21].”
MIMIC-IV, a freely accessible electronic health record dataset
Johnson, A. E. W., Bulgarelli, L., Shen, L., Gayles, A., Shammout, A., Horng, S., Pollard, T. J., Hao, S., Moody, B., Gow, B., et al. (2023) · Scientific Data · doi:10.1038/s41597-022-01899-x · Cited by 3,401 · cited 2×
“When pretrained on large-scale biomedical corpora such as the medical information mart for intensive care (MIMIC)-III clinical data [17] or medical literature, LLMs acquire domain-specific language understanding.”
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-T., Rocktäschel, T., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.11401 · Cited by 3,101 · cited 1×
“Introduced in 2020, Retrieval-Augmented Generation (RAG) mitigates these limitations by combining a retriever which accesses external sources such as clinical guidelines or EHRs with a generator that conditions responses on both the query and retrieved content [8].”
Domain-specific language model pretraining for biomedical natural language processing
Gu, Y., Tinn, R., Cheng, H., Lucas, M., Usuyama, N., Liu, X., Naumann, T., Gao, J., & Poon, H. (2022) · ACM Transactions on Computing for Healthcare · doi:10.1145/3458754 · Cited by 2,170 · cited 1×
“These systems use biomedical embeddings (e.g., BioBERT, PubMedBERT [30]), specialized corpora (e.g., PubMed abstracts and clinical notes), and domain-specific knowledge bases (e.g., unified medical language system (UMLS), MIMIC).”
Toward expert-level medical question answering with large language models
Singhal, K., Tu, T., Gottweis, J., Sayres, R., Wulczyn, E., Amin, M., Hou, L., Clark, K., Pfohl, S. R., Cole-Lewis, H., et al. (2025) · Nature Medicine · doi:10.1038/s41591-024-03423-7 · Cited by 1,734 · cited 1×
“To address these challenges, medical domain-specific LLMs such as Medical Path-ways Language Model (Med-PaLM) [2] and Biomedical Generative Pretrained Transformer (BioGPT) [3] have shown improved performance across various clinical natural language processing (NLP) tasks, including question…”
Research works printed but not linked: 3
- 12. Gaur, M. Knowledge-Infused Learning. Ph.D. Thesis, University of South Carolina, Columbia, SC, USA, 2022.
- 31. Kirubakaran, S.S.; Kathrine, J.W.G.; Kanaga, G.M.; Raja, M.J.; Singh, R.G.; Yuvaraajan, E. A RAG-based Medical Assistant Especially for Infectious Diseases. In Proceedings of the 2024 International Conference on Inventive Computation Technologies (ICICT), Lalitpur, Nepal, 24-26 April 2024; pp. 1128-1133. [CrossRef]
- 52. Yu, H.; Guo, P.; Sano, A. Zero-Shot ECG Diagnosis with Large Language Models and Retrieval-Augmented Generation. In Proceedings of the 3rd Machine Learning for Health Symposium, PMLR, Orleans, LA, USA, 10 December 2023; Volume 225, pp. 650-663.
Cited by
Simou, E. (2025) · International Medical Education · doi:10.3390/ime4040050 · Cited by 35
“By retrieving verifiable evidence and displaying inline citations, RAG architectures further enhance epistemic trust and accountability, enabling learners to appraise the provenance, coherence, and ethical dimensions of AI-generated reasoning critically [159,160].”
InfluentialWołk, K. (2025) · Electronics · doi:10.3390/electronics14214227 · Cited by 27
“The system requires both retrieval and generation operations to finish within 2 s for clinical workflow integration [7].”
Stuhlmiller, T. J., Rabe, A., Rapp, J., Awawda, A., Kouser, H., Lui, K., Salamon, H., Chuyka, D., Mahoney, W., Furgason, J. M., et al. (2025) · medRxiv · doi:10.1101/2025.02.25.25322898 · Cited by 13
Gkousis, S., Vasilaki, V., & Katsou, E. (2025) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2025.116577 · Cited by 14
Saidu, F. A., & Wall, J. (2026) · Electronics · doi:10.3390/electronics15030555 · Cited by 9
“In line with the G7 AI Code of Conduct, which advocates continuous risk assessment and transparency, the study prioritised transparency in its methodologies and results [36,37].”
Pandian, V., Rahimibashar, F., Arabfard, M., Alhalaiqa, F., & Vahedian‐Azimi, A. (2026) · Intensive and Critical Care Nursing · doi:10.1016/j.iccn.2025.104323 · Cited by 7
Application of knowledge graphs in rare disease research
Fei, Y., Ding, H., Tong, S., He, Y., & Cai, W. (2026) · Frontiers in Public Health · doi:10.3389/fpubh.2026.1757612 · Cited by 8
Enhancing Medical Question Answering with LLMs via a Hybrid Retrieval-Augmented Generation Framework
Aljohani, B., & Alsanoosy, T. (2026) · Information · doi:10.3390/info17020133 · Cited by 3
Emssaad, I., Ben-Bouazza, F.-E., Tafala, I., Mezali, M. C. E., & Jioudi, B. (2025) · Computer Methods and Programs in Biomedicine Update · doi:10.1016/j.cmpbup.2025.100221 · Cited by 2
Lin, S., shao, S., Liu, X., & Su, H. (2026) · Information · doi:10.3390/info17020138 · Cited by 2
Vicente-Martínez, P., Soria‐Olivas, E., Esteve-Mompó, I., Sánchez-Montañés, M. A., García-Escrivà, M. Á., & William, E. (2026) · AI · doi:10.3390/ai7040123 · Cited by 7
Natural Language Processing in Healthcare: From Unstructured Data to Clinical Intelligence
Kumar, D., Choudhary, N., Gupta, V., Tanwar, R., Bahmani, K., Antal, S., Jarora, S., Gupta, S., Shaikh, M. S., Webster, T. J., et al. (2026) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2026.200698 · Cited by 3
Zhao, Y., Guo, R., Miao, Y., Luo, Y., Wang, H., & Wu, Y. X. (2026) · Journal of Medical Internet Research · doi:10.2196/89190 · Cited by 2
“In practice, generative delivery was concentrated in explanatory, interpretive, and socioemotional functions, whereas prompts, structured self-monitoring, and some safety-sensi-tive processes remained more likely to rely on deterministic rules or templates [80-86].”
Privacy-by-Design Framework for Large Language Model Chatbots in Urology
Kim, E. J., & Kim, J. (2025) · International Neurourology Journal · doi:10.5213/inj.2550274.137 · Cited by 2
Fine-Tuning MedGemma for Clinical Captioning to Enhance Multimodal RAG over Malaysia CPGs
Zun, L. Q., Halim, M. Z. B. A., & Fye, G. M. (2025) · IEEE Conference on Systems, Process and Control · doi:10.1109/icspc68261.2025.11326535 · Cited by 3
“Retrieval-Augmented Generation (RAG) has emerged as a robust solution, mitigating this risk by grounding outputs in verifiable sources like the Malaysian CPGs to enable factual, trustworthy guidance [5][6][7][35].”
Ahmed, M. M., Okesanya, O. J., Othman, Z. K., Adebayo, U. O., Oso, T. A., & Lucero‐Prisno, D. E. (2026) · Informatics and Health · doi:10.1016/j.infoh.2026.03.002 · Cited by 1
Căliman-Sturdza, O. A., Gheorghita, R. E., Filip, R., & Lobiuc, A. (2026) · Diagnostics · doi:10.3390/diagnostics16121827 · Cited by 5
“…post-deployment monitoring [6]; the FDA lifecycle guidance on AI-enabled device software functions extends predicate-device thinking to model updates and drift [37]; and the EU AI Act classifies most clinical LLMs as high-risk systems with attendant conformity obligations under MDR/IVDR [104,105].”
Joachim, M. V., Rushinek, H., & Laviv, A. (2026) · International Journal of Oral and Maxillofacial Surgery · doi:10.1016/j.ijom.2026.06.010 · Cited by 3
An equity-aware generative AI copilot for digital public health surveillance
Albahli, S. (2026) · Frontiers in Public Health · doi:10.3389/fpubh.2026.1827709 · Cited by 1
Chapellier, P., Ferrari, J., Saliba, T., Jeltsch, P., Mohamed, M., Jankowski, S., Ilanjian, G., Epis, M., Pansini, V., Bragaglia, F., et al. (2026) · Diagnostics · doi:10.3390/diagnostics16132009 · Cited by 2
“As reviewed in healthcare applications [32], RAG frameworks drastically reduce errors by anchoring the LLM to an authoritative database.”
Suzgen, E. E., Şahin, M. E., Bakir, M., Arisoy, Ç., Ulutaş, E. G., Günay, R. B., Yildiz, G., & Ulutaş, H. (2026) · 2026 2nd International Symposium on AI-Driven Engineering Systems (ISADES) · doi:10.1109/isades69945.2026.11608117
“In medical settings, RAG has been shown to improve factual consistency and reduce hallucinations, though corpus quality remains a critical factor [19].”
Barki, C., Chouchen, M., Sediri, A., Ceylan, H. İ., Rahmouni, H. B., Muntean, R. I., El-Seedi, H. R., Bragazzi, N. L., & Dergaa, I. (2026) · Frontiers in Systems Biology · doi:10.3389/fsysb.2026.1892418 · Cited by 1
“The LLM component, grounded in clinical epidemiology databases through RAG, provides causal annotation for each SHAP-ranked factor, distinguishing established causal risk factors from confounded associations and calibrating recommendation strength accordingly (Neha et al., 2025).”
Inaugural Editorial for Computational Biomedicine
Huang, D.-S. (2025) · Computational Biomedicine · doi:10.70401/cbm.2025.0002
Performance of reasoning large language models on nephrology multiple-choice questionsPreprint
Kitano, F., Masaki, M., Ichikawa, D., Shibagaki, Y., & Noda, R. (2025) · medRxiv · doi:10.64898/2025.12.03.25341427
Younis, H., Younis, H., Sharjeel, M., Azeem, M., & Minghim, R. (2025) · International Conference on Open Source Systems and Technologies (ICOSST) · doi:10.1109/icosst69113.2025.11315415 · Cited by 1
“Early systems demonstrated the feasibility of automatically identifying relations from large corpora, and domain-specific language models, such as BioBERT (a BERT model pretrained on biomedical text) [6], improved the recognition of biomedical entities and terminology [2].”
Ahishakiye, E., & Rugambwa, N. O. (2025) · Research Square · doi:10.21203/rs.3.rs-8337646/v1
He, K., Xiao, Q., Chen, W., Jing, L., Wang, Y., Li, S., Yang, D., Xu, H., Pang, K., Xiao, R., et al. (2026) · doi:10.2196/preprints.92852
MAPFM: A Multi-Agent Retrieval-Augmented Framework for Medical Text Classification
Gu, Y. (2025) · International Conference on Smart Healthcare and Wearable Intelligent Devices (SHWID) · doi:10.1145/3788112.3788145
“RAG technology effectively compensates for the knowledge gaps of LLMs in specialized domains through a process involving retrieval from external knowledge bases, relevant information filtering, and content generation [16].”
Shoumi, M. N., Harada, K., Oshita, H., Sakashita, S., & Inoue, S. (2026) · doi:10.2196/preprints.93374
Enhancing Chatbot Performance with Retrival-Augmented Generation and Query Expansion
Id, I. D., Aminuddin, A., Mahdiyah, E., Hidayat, R., Sy, Y. S., & Okmayura, F. (2025) · Beyond Technology Summit on Informatics International Conference (BTS-I2C) · doi:10.1109/bts-i2c67944.2025.11399515 · Cited by 1
“Its retrieval mechanism also enables dynamic access to real-time knowledge, extending the system’s capacity beyond the static limits of training data[6], [7], [8].”
Reimagining Reality: Innovations in AI Hallucination Management and Trustworthy Generation
Nag, A., & Chaudhuri, D. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7534-2.ch012 · Cited by 1
Generative Simulation and Summarization of Neonatal Patient Data
Levine, J., Riarh, G., & Green, J. R. (2026) · Information · doi:10.3390/info17030261
Kocbek, P., Frkatović-Hodžić, A., Lalić, D., Hui, V. C. C., Lauc, G., & Štiglic, G. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11401037 · Cited by 1
Hanzawa, M., Hasei, J., Okada, A., Tanaka, C., Shigeyasu, Y., Fujii, C., Horiuchi, M., Sugihara, A., Takeuchi, K., Nakahara, R., et al. (2026) · Frontiers in Digital Health · doi:10.3389/fdgth.2026.1759690 · Cited by 4
“To mitigate these risks while leveraging the strengths of LLMs, retrieval-augmented generation (RAG) has been proposed, which constrains response generation to a domain-specific knowledge base (21).”
Greyling, C., Joubert, J., Kapp, E., Ebrahim, N., Maart, R., Tucker, W. D., ZYL, D. J. V., Mhlongo, N., Dhlamini, M. S., Peck, A., et al. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01098-2 · Cited by 1
Retrieval as governance: A medical informatics perspective on clinical large language models
Wang, B., Wang, Z., & Zhong, Y. (2026) · Digital Medicine · doi:10.1097/dm-2026-00009
Czy to koniec pracy socjalnej, jaką znamy? Refleksyjna praktyka w dobie sztucznej inteligencji
Necel, R. (2026) · Praca Socjalna · doi:10.71358/ps.2851
Albahli, S. (2026) · Mathematics · doi:10.3390/math14071179
Generative models for clinical entity linking in Spanish
Zotova, E., Cuadros, M., & Rigau, G. (2026) · Array · doi:10.1016/j.array.2026.100805
AI-Powered Personalized Medication Recommender by Using RAG
Manohar, S., Kumar, A., & Chandrika, L. (2026) · International Conference on Communication, Computing and Emerging Technologies (IC3ET) · doi:10.1109/ic3et64989.2026.11467324
“It brings in massive amounts of data patient history, symptoms, genetic, life history, and environmental history to create an actual customization of treatment plans [6], [10].”
STAnalyzer: Transparent Spatial Transcriptomics Analysis via an Agentic ArchitecturePreprint
Luo, H., Liu, L., Zhijin, X. I. N. G., Li, X., Zhang, X., Du, W., Liu, B., Wang, J., & Yu, G. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.04.06.716827 · Cited by 1
“Lacking mechanisms for query alignment or coarse-to-fine reading, they cannot retrieve high-fidelity evidence, rendering them unable to provide the traceable, citation-backed insights required to distinguish genuine biological discoveries from technical artifacts [18].”
RAG - In Hospital Management System
Karthik, N. A., Mythily, M., Ebenezer, V., Jerlin Rajan, J., Reeves, S. J., & SheebaThangapushpam, C. (2026) · International Conference on Multi-Agent Systems for Collaborative Intelligence (ICMSCI) · doi:10.1109/icmsci67830.2026.11469411
“Adding local FAISS index and patient-scoped retrieval to The proposed approach opens up this gap and puts the recommendations of the survey from a conceptual level into engineering practice [2].”
Stelling, H., Kraus, A., Grieb, G., Breidung, D., & Güler, I. (2026) · Life · doi:10.3390/life16040681 · Cited by 1
“…directions include retrieval-augmented generation (RAG), which has shown promise for grounding model outputs in verified clinical knowledge in other medical domains [36,37], tool-augmented inference, and hybrid pipelines combining visual feature extraction with structured clinical reasoning.”
Adamyan, L. V., Plavunov, I. N., & Владимировна, К. О. (2026) · Russian Journal of Human Reproduction · doi:10.17116/repro2026320216
Tapia-Mendez, E., Cruz-Albarrán, I. A., Tovar‐Arriaga, S., González‐Islas, D., Orea‐Tejeda, A., & Morales-Hernandez, L. A. (2026) · AI · doi:10.3390/ai7050155
Implementation of Generative AI in Biomedical Research and Healthcare
Nikolopoulos, A., & Karalis, V. D. (2026) · Applied Biosciences · doi:10.3390/applbiosci5020034
“…of relying solely on a model’s static, pre-trained parametric memory, RAG dynamically retrieves up-to-date, authoritative external data to help inform AI’s response based on verifiable evidence (e.g., peer-reviewed PubMed articles, clinical guidelines, or structured electronic health records) [94].”
NEURON: A Neuro-symbolic System for Grounded Clinical Explainability
Chandrasekaran, A., Zikos, D., Mete, M., Pang, A., Lund, B. D., & Sha, K. (2026) · IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies · doi:10.1109/chase69719.2026.00012 · Cited by 3
“Hence, using a RAG layer to ground LLMs in domain knowledge helps maintain factual accuracy [54, 70].”
Sharma, K., Srivastava, S., -, S. S., & Singhal, A. (2026) · IEEE International Conference on AI Engineering and Innovations (AIEI) · doi:10.1109/aiei69164.2026.11497629 · Cited by 1
“Current RAG frameworks largely depend on single-stage, single-source retrieval processes and do not verify whether produced solutions are completely supported by collected evidence [5].”
O-Rag Ontology-Enhanced Retrieval-Augmented Generation For The Uzbek Legal Domain
Absalamova, D., Muminov, B. B., & Absalamova, G. B. (2025) · International Conference on Future Networks and Distributed Systems (ICFNDS) · doi:10.1145/3789692.3789782
“Although the retriever, which is commonly applied in sparse retrieval models such as TF-IDF/BM25 [5] or dense passage retrieval (DPR) models [6], also retrieves relevant background to a specific query, the retriever is tasked with the role of retrieving this information.”
A Streamlined AI-Powered Workflow for Enriching Library Newspaper Archives
Varthis, E. (2026) · Journal of Web Librarianship · doi:10.1080/19322909.2026.2638177
“The structured texts were automatically converted into vectors using vector-embedding models and building a Retrieval-Augmented Generation (RAG) system (Neha et al., 2025).”
Jeong, E., Jeong, W., Song, E., Park, E. H., Oh, K. H., & Jun, J. K. (2026) · Digital Health · doi:10.1177/20552076261450314
Assessing the Impact of AI-Augmented DevSecOps on Lead Time in Agile Release Management
Gunawan, J. A., Singgih, M. L., & Ginardi, R. V. H. (2026) · F1000Research · doi:10.12688/f1000research.178067.1 · Cited by 1
He, K., Xiao, Q., Chen, W., Jing, L., Wang, Y., Li, S., Yang, D., Xu, H., Pang, K., Xiao, R., et al. (2026) · Journal of Medical Internet Research · doi:10.2196/92852
Oleh, U., Obermaisser, R., Machulska, A., & Klucken, T. (2026) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-032-24724-7_29
Retrieval-Augmented Generation for Pharmaceutical Regulatory Intelligence: A Narrative Review
Bianchi, L., Rossi, M., & Romano, G. (2026) · Pharmacophore · doi:10.51847/sma6gzncaq
Ghanem, O. M., MacTaggart, P., Alamy, N. H., & Ghusn, W. (2026) · Surgery for Obesity and Related Diseases · doi:10.1016/j.soard.2026.05.026
Wang, Q., Xu, X., Li, X., Mou, L., Cui, C., Zhai, L., Wong, R. M. Y., Cheung, W. H., & Zhang, N. (2026) · AI · doi:10.3390/ai7060201 · Cited by 1
“…addresses the static training limitations of LLMs by enforcing factual consistency; however, implementing RAG in clinical settings requires overcoming specific technical hurdles, such as generation latency and the “noise” inherent in retrieving data from highly heterogeneous medical records [73].”
LLM-Based Personalized Medical Chatbot Enhancing Credibility and User-Centric Healthcare
Sucharitha., P., Kranthi Kumar, G., & Tejaswini., Y. (2026) · International Conference on Trends in Electronics and Informatics (ICOEI) · doi:10.1109/icoei68323.2026.11541460
“[18].”
Prabha, S., Collaço, B. G., Gomez-Cabello, C. A., Haider, S. A., Genovese, A., Fang, Z., Wood, N. G., Bagaria, S. P., Tao, C., & Forte, A. J. (2026) · Journal of Medical Internet Research · doi:10.2196/90692 · Cited by 1
Nurfadhilah, E., Aini, L. R., Santosa, A., Uliniansyah, M. T., Gunarso, G., Putra, P. K., Pebiana, S., Fajri, R., Hidayati, N. N., Prastowo, R. D., et al. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7862-6.ch003
AI-Driven Welfare Scheme Recommendation Using Random Forest and RAG
A.karunamurthy, & S.Barath (2026) · International Journal of Latest Technology in Engineering Management & Applied Science · doi:10.51583/ijltemas.2026.150500196
Benito, K. K. A., Corpuz, R. C. P., Gonzales, A. M., & Comia, L. V. (2026) · International Conference on Integrated Intelligence and Cognitive Engineering (ICIICE) · doi:10.1109/iciice69672.2026.11565138
“Recent studies in biomedical and healthcare informatics indicate that RAG-based systems can significantly improve answer faithfulness and usability when applied to domain-specific knowledge sources, although careful system design and evaluation remain essential [6].”
Legado, N. K. M., Villar, L. J. A., & Comia, L. V. (2026) · International Conference on Integrated Intelligence and Cognitive Engineering (ICIICE) · doi:10.1109/iciice69672.2026.11565253
“First RAG integrates a generative language model with an external retrieval mechanism that accesses a curated knowledge base [7]-[8].”
Heimbruch, H. H. H., Solomon, W. T., Junaid, S. A., Eke, D. O., Tata, L., Oluwadare, O. E., & Shehu, H. (2026) · Epidemiology and Health Data Insights · doi:10.63946/ehdi/18797
“The retrieval layer accesses prior notes, labs, medications, allergies, and problem lists, often using retrieval-augmented generation (RAG) techniques to anchor note content in patient-specific context [12, 19, 20].”
Paul, B., Nandi, A., Roy, D. G., & Datta, P. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-44344-2.00020-0
García-López, I. M., Espinosa, J. M. M., & Soledad, M. (2026) · IEEE Revista Iberoamericana de Tecnologias del Aprendizaje · doi:10.1109/rita.2026.3701046
Automatic ICD-10 Classification in Neonatology
Sheka, A., Chensky, G., & Prutkin, M. (2026) · Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT) · doi:10.1109/usbereit70063.2026.11580517
“RAG systems are being actively implemented in medicine: Neha et al. [13] note their ability to minimise LLM ‘hallucinations’ and ensure the explainability of responses; Yang et al. [14] demonstrate the potential of RAG for clinical practice; Son et al. [15] developed a chatbot based on electronic…”
A Dual-source Fusion Enhancement method for Question Answering on Acute Mountain Sickness
Sui, M., Bi, X., Yu, G., Zhang, L. H., Xu, H., & Zhao, K. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582261
“Its value is particularly pronounced in the medical domain, where factual precision is crucial [19], [20].”
MedConf-RAG: Reliable Medical LLMs with Gated Graph Integration and Conformal Factuality Guarantees
Huang, X., Bu, Y., Zhang, N., Zhang, Y., Sheng, H., & Li, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2856-0_39 · Cited by 1
Ayalew, A. M., Seppänen, T., & Oussalah, M. (2026) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3805713.3820416
Stalp, J. L., Schneider, J. A., Krause, A., STEINKASSERER, L., Hachenberg, J., Denecke, A., Hillemanns, P., & Wolff, D. (2026) · Frontiers in Digital Health · doi:10.3389/fdgth.2026.1896184
“RAG can anchor model responses in curated sources such as guidelines, institutional protocols, and peer-reviewed literature, thereby improving factual consistency and reducing unsupported claims (26).”
Rogers, C., Alqadri, A., Beaton, F., & Moshfeghi, Y. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3808546
Robust Medical Text Correction via Domain Adaptation and Term-Aware Safety Control
Yin, B., & Huang, S. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3417-2_22
Voice, Speech, and Large Language Models in Neurology: From Acoustic Biomarkers to Conversational AI
Shelly, S. (2026) · Computation · doi:10.3390/computation14070160
Omar, N., Vengadeswaran, S., & Mohamedsipli, M. (2026) · International Conference on Signal Processing and Communications (SPCOM) · doi:10.1109/spcom71105.2026.11622975
“A RAG module answers natural-language caregiver queries by retrieving from a Pinecone vector store of patient notes and clinical literature (full configuration in Table I) [14], [23].”
Santoso, B. E., Soeparno, H., Arifin, Y., & Gaol, F. L. (2026) · International Conference on Intelligent Engineering and Next-Gen Healthcare Systems (IEHNS) · doi:10.1109/iehns68708.2026.11607400
“This problem raises concern that the information generated by AI is not trustworthy, especially in domains requiring verifiable evidence such as healthcare, finance, and education [3], [4], [5].”
Agentic Medical Intake Information Assistant
Yadav, A., Gupta, S., Shukla, A., Jain, M., & Gambhir, S. (2026) · IEEE Global Symposium on Emerging and Communication Technologies (GSEACT) · doi:10.1109/gseact68539.2026.11620021
“Retrieval-Augmented Generation can solve this by making sure that the outputs are based on reliable sources [6], [22].”
Recent trends of retrieval-augmented generation in healthcare: A systematic review
Landolsi, M. Y., Fadhli, I., Boufaied, A., & Romdhane, L. B. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115912
SmartMM: A Domain-Specific Large Language Model for Medical Microbiology
Gong, Y., Ma, R., Wang, X., Li, R., Dong, H., Liu, Y., Peng, X., GUO, Q., & Liu, Y. (2026) · AI · doi:10.3390/ai7080316
An LLM and Retrieval Pipeline for Reproductive-Health Misinformation and Stigma
Behnamian, S., Shahbazi, Z., Fogh, F., Baghestani, B., Khani, A., & Rostami, A. D. (2026) · Reproductive Medicine · doi:10.3390/reprodmed7030042
RADE: Responsibility-aware decoding of evidence for robust retrieval-augmented generation
Yin, L., Cheng, Y., Du, X., Wang, Z., Zheng, Y., & Li, F. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.133898
An Agentic Risk-Aware QA Framework for Smart Elderly Care
Shang, C., Wen, W., & Chang, C. (2026) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-taiwan71481.2026.11652771
HealthQ: A Retrieval-Augmented Health Policy Query Chatbot
Joshi, V., Tyagi, U., Jakhar, V., Gaur, M., & Garg, P. (2026) · International Conference on Emerging VLSI and Semiconductor Technology for AI and Computing Applications (EVST) · doi:10.1109/evst69093.2026.11660654
Kow, P. E., & Kow, P.-Y. (2026) · Results in Engineering · doi:10.1016/j.rineng.2026.112663
Blackwell: An Explainable Anamnesis-Based Multi-agent Framework for Remote Clinical Diagnosis
Torquato, L., Haque, R., Stynes, P., Doyle, G., & Cawley, O. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37249-9_52
Digital Health Revolution in Saudi Arabia: A Narrative Review of Healthcare Transformation
Shahin, M. A. H. (2026) · Healthcare · doi:10.3390/healthcare14172810 · Cited by 1
“It has been successfully applied in prenatal care and mental health [70], increasing treatment adherence and completion [71].”
InfluentialWang, T., Tan, J.-Y. (., Li, M., Wang, H., Sharma, S., & Terry, D. R. (2026) · Nursing Reports · doi:10.3390/nursrep16090315
“From an implementation perspective, the integration of LLMs and RAG pipelines into primary care settings underscores the importance of socio-technical alignment [51,52].”
InfluentialRaj, A., Hasan, M., & Shahadat, S. B. (2026) · Journal of Pharmaceutical Analysis · doi:10.1016/j.jpha.2026.101783 · Cited by 1
Correia, G. G., Ferraz, F., & Alves, V. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-32729-1_3
Evaluating an AI-assisted triage workflow for retinal diseases
Park, D., Oh, R., Baek, J., & Bae, K. (2026) · PLOS Digital Health · doi:10.1371/journal.pdig.0001700
TA-RAG: A Time-Aware Retrieval-Augmented Generation Framework for Chronic Disease Management
Li, C., & Liu, B. (2026) · International Conference on Health Big Data · doi:10.1145/3833450.3833504
Arafin, P., Moniruzzaman, M., & Alkhateeb, A. (2026) · Applied Sciences · doi:10.3390/app16189148 · Cited by 1
Sečujski, M., Vujinović, A., Kovačević, A., Simić, N., Stanojev, V., Suzić, S., Nosek, T., & Delić, V. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37867-5_12
Cavasin, A. M., Benedetti, A. R. T., Bellei, E. A., & Marchi, A. C. B. D. (2026) · IEEE Access · doi:10.1109/access.2026.3734862
“Retrieval-augmented architectures have moved in the same direction, adding validation steps because grounding alone does not guarantee that a retrieved passage is used correctly [18], [19].”
InfluentialNguyen, B. T., Pham, H. V., Tran, T. K., & Dao, S. V. T. (2026) · Intelligence-Based Medicine · doi:10.1016/j.ibmed.2026.100467
ENAYATI, M., Priya, V., Prochaska, E., Sobe, K., & Wolfien, M. (2026) · Sci · doi:10.3390/sci8090266
“New guidelines, revised SOPs, updated marker databases, additional publications, or newly available patient documents can be added to the retrieval layer, while the model backend remains exchangeable [9].”
Mohamed, H. A., Mohamud, D. A., Mohamed, Z. A., & Hirsi, A. M. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-02180-5
“Broader LLM comparisons caution that benchmark behaviour varies across model families [5], FAISS provides the dense-vector search mechanism used in many retrieval pipelines [6], and healthcare RAG studies show why retrieval and generation controls must be reported separately [2, 7].”
InfluentialWang, G., Bi, H., Zhang, Y., Wang, W., Zhu, Y., Wang, C., & Yang, X. (2026) · Diagnostics · doi:10.3390/diagnostics16193100
Metadata
- Authors
- Neha, F., Bhati, D., & Shukla, D. K.
- Affiliations
- Kent State University (US)
- Rutgers, The State University of New Jersey (US)
- Corresponding author
- Neha, Fnu
- Venue
- AI
- Publisher
- MDPI AG
- Published
- 2025-09-11
- Volume
- 6
- Issue
- 9
- Pages
- 226
- ISSN
- 2673-2688 (ISSN-L)
- OpenAlex
- W4414128336
- Cited by
- 117
- References
- 55
- Citations by year
- 2026: 103 · 2025: 14
- FWCI
- 27.92
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- AI (publishedVersion, cc-by)
- Preprints.org (acceptedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Kent State University’s Open Access APC Support Fund
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Keywords
- retrieval-augmented generation, health care, large language models, hallucination mitigation, medical question answering, domain shift, explainability
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.



