Title and abstract screening for literature reviews using large language models: an exploratory study in the biomedical domain
Open accessThe DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.
Abstract
Background: Systematically screening published literature to determine the relevant publications to synthesize in a review is a time-consuming and difficult task. Large language models (LLMs) are an emerging technology with promising capabilities for the automation of language-related tasks that may be useful for such a purpose. Methods: LLMs were used as part of an automated system to evaluate the relevance of publications to a certain topic based on defined criteria and based on the title and abstract of each publication. A Python script was created to generate structured prompts consisting of text strings for instruction, title, abstract, and relevant criteria to be provided to an LLM. The relevance of a publication was evaluated by the LLM on a Likert scale (low relevance to high relevance). By specifying a threshold, different classifiers for inclusion/exclusion of publications could then be defined. The approach was used with four different openly available LLMs on ten published data sets of biomedical literature reviews and on a newly human-created data set for a hypothetical new systematic literature review. Results: The performance of the classifiers varied depending on the LLM being used and on the data set analyzed. Regarding sensitivity/specificity, the classifiers yielded 94.48%/31.78% for the FlanT5 model, 97.58%/19.12% for the OpenHermes-NeuralChat model, 81.93%/75.19% for the Mixtral model and 97.58%/38.34% for the Platypus 2 model on the ten published data sets. The same classifiers yielded 100% sensitivity at a specificity of 12.58%, 4.54%, 62.47%, and 24.74% on the newly created data set. Changing the standard settings of the approach (minor adaption of instruction prompt and/or changing the range of the Likert scale from 1–5 to 1–10) had a considerable impact on the performance. Conclusions: LLMs can be used to evaluate the relevance of scientific publications to a certain review topic and classifiers based on such an approach show some promising results. To date, little is known about how well such systems would perform if used prospectively when conducting systematic literature reviews and what further implications this might have. However, it is likely that in the future researchers will increasingly use LLMs for evaluating and classifying scientific publications.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
An overview of clinical decision support systems: Benefits, risks, and strategies for success
Sutton, R. T., Pincock, D., Baumgart, D. C., Sadowski, D. C., Fedorak, R. N., & Kroeker, K. I. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-0221-y · Cited by 3,019 · cited 1×
“This general definition may include diagnostic tools, knowledge bases, prognostic models, or patient decision aids [50].”
BackgroundAyers, J. W., Poliak, A., Dredze, M., Leas, E. C., Zhu, Z., Kelley, J. B., Faix, D. J., Goodman, A. M., Longhurst, C. A., Hogarth, M., et al. (2023) · JAMA Internal Medicine · doi:10.1001/jamainternmed.2023.1838 · Cited by 2,613 · cited 1×
“Recent technological advancements in model size, architecture, and training strategies have led to general-purpose dialog LLMs achieving and exceeding state-of-the-art performance on many benchmark tasks including medical question answering [16] and text summarization [17].”
BackgroundSiddaway, A. P., Wood, A. M., & Hedges, L. V. (2019) · Annual Review of Psychology · doi:10.1146/annurev-psych-010418-102803 · Cited by 2,550 · cited 1×
“To overcome this issue, SLRs of high quality require multiple independent researchers to do the evaluation with specific criteria upon inclusion/exclusion defined beforehand [56].”
BackgroundA Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Dong, Z., Hou, Y., Zhang, B., Min, Y., Zhang, J., Liu, P., et al. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-026-60308-3 · Cited by 2,093
A Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.18223 · Cited by 2,090
Scaling Instruction-Finetuned Language Models
Chung, H. W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, Y., Wang, X., Dehghani, M., Brahma, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.11416 · Cited by 1,441
An open source machine learning framework for efficient and transparent systematic reviews
van de Schoot, R., de Bruin, J., Schram, R., Zahedi, P., de Boer, J., Weijdema, F., Kramer, B., Huijts, M., Hoogerwerf, M., Ferdinands, G., et al. (2021) · Nature Machine Intelligence · doi:10.1038/s42256-020-00287-7 · Cited by 1,157
Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm
Reynolds, L., & McDonell, K. (2021) · Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411763.3451760 · Cited by 952 · cited 2×
“Furthermore, they can be flexibly adapted via prompt engineering techniques [25] and parameter settings, to behave in a desired way.”
BackgroundMethodA full systematic review was completed in 2 weeks using automation tools: a case study
Clark, J., Glasziou, P., Del Mar, C., Bannach-Brown, A., Stehlik, P., & Scott, A. M. (2020) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2020.01.008 · Cited by 687 · cited 1×
“Thus, the automation or semi-automation of this part of the reviewing workflow has been of longstanding interest [3–5].”
BackgroundMarshall, I. J., & Wallace, B. C. (2019) · Systematic Reviews · doi:10.1186/s13643-019-1074-9 · Cited by 638 · cited 1×
“A variety of different ML and AI tools have been developed to assist researchers in performing SLRs [5, 10, 52, 53].”
BackgroundZack, T., Lehman, E., Suzgun, M., Rodriguez, J. A., Celi, L. A., Gichoya, J., Jurafsky, D., Szolovits, P., Bates, D. W., Abdulnour, R.-E. E., et al. (2024) · The Lancet Digital Health · doi:10.1016/s2589-7500(23)00225-x · Cited by 510 · cited 1×
“At the same time, considerable problems with the usage of LLMs such as “hallucinations” of models [26], inherent biases [27, 28], and weak alignment with human evaluation [29] have been described.”
BackgroundHarrison, H., Griffin, S. J., Kuhn, I., & Usher-Smith, J. A. (2020) · BMC Medical Research Methodology · doi:10.1186/s12874-020-0897-3 · Cited by 449
Evaluating large language models on medical evidence summarization
Tang, L., Sun, Z., Idnay, B., Nestor, J. G., Soroush, A., Elias, P. A., Xu, Z., Ding, Y., Durrett, G., Rousseau, J. F., et al. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00896-7 · Cited by 423
Evaluating Large Language Models on Medical Evidence Summarization
Tang, L., Sun, Z., Idnay, B., Nestor, J. G., Soroush, A., Elias, P. A., Xu, Z., Ding, Y., Durrett, G., Rousseau, J., et al. (2023) · doi:10.1101/2023.04.22.23288967 · Cited by 423 · cited 1×
“Recent technological advancements in model size, architecture, and training strategies have led to general-purpose dialog LLMs achieving and exceeding state-of-the-art performance on many benchmark tasks including medical question answering [16] and text summarization [17].”
BackgroundOpenAI ChatGPT Generated Literature Review: Digital Twin in Healthcare
Aydın, Ö., & Karaarslan, E. (2022) · doi:10.2139/ssrn.4308687 · Cited by 391 · cited 1×
“Aydin et al., also using ChatGPT, employed the LLM to write an entire Literature Review about Digital Twins in Healthcare [61].”
MethodSemi-automated screening of biomedical citations for systematic reviews
Wallace, B. C., Trikalinos, T. A., Lau, J., Brodley, C., & Schmid, C. H. (2010) · BMC Bioinformatics · doi:10.1186/1471-2105-11-55 · Cited by 351
Can Large Language Models Be an Alternative to Human Evaluations?
Chiang, C.-H., & Lee, H.-Y. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.870 · Cited by 331
Can Large Language Models Be an Alternative to Human Evaluations?
Chiang, C.-H., & Lee, H.-Y. (2023) · arXiv · doi:10.48550/arxiv.2305.01937 · Cited by 331
Wolters, F. J., Segufa, R. A., Darweesh, S. K. L., Bos, D., Ikram, M. A., Sabayan, B., Hofman, A., & Sedaghat, S. (2018) · Alzheimer's & Dementia · doi:10.1016/j.jalz.2018.01.007 · Cited by 293
Can ChatGPT Write a Good Boolean Query for Systematic Review Literature Search?
Wang, S., Scells, H., Koopman, B., & Zuccon, G. (2023) · Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3539618.3591703 · Cited by 275 · cited 1×
“For example, Wang et al. obtained promising results when investigating if ChatGPT may be used for writing Boolean Queries for SLRs [60].”
MethodAutomated Paper Screening for Clinical Reviews Using Large Language Models
Guo, E., Gupta, M., Deng, J., Park, Y.-J., Paget, M., & Naugler, C. (2023) · arXiv · doi:10.48550/arxiv.2305.00844 · Cited by 230
Revisiting Relation Extraction in the era of Large Language Models
Wadhwa, S., Amir, S., & Wallace, B. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.868 · Cited by 207
Automated paper screening for clinical reviews using large language models: Data analysis study
Guo, E., Gupta, M., Deng, J., Park, Y.-J., Paget, M., & Naugler, C. (2024) · Journal of Medical Internet Research · doi:10.2196/48996 · Cited by 205
Tools to support the automation of systematic reviews: a scoping review.
Khalil, H., Ameen, D., & Zarnegar, A. (2022) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2021.12.005 · Cited by 190
Using ChatGPT to conduct a literature review
Haman, M., & Školník, M. (2024) · Accountability in Research · doi:10.1080/08989621.2023.2185514 · Cited by 144
Hallucinations in Large Multilingual Translation Models
Guerreiro, N. M., Alves, D. M., Waldendorf, J., Haddow, B., Birch, A., Colombo, P., & Martins, A. F. T. (2023) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00615 · Cited by 124
Hallucinations in Large Multilingual Translation Models
Guerreiro, N. M., Alves, D., Waldendorf, J., Haddow, B., Birch, A., Colombo, P., & Martins, A. F. T. (2023) · arXiv · doi:10.48550/arxiv.2303.16104 · Cited by 124
Hamel, C., Hersi, M., Kelly, S. E., Tricco, A. C., Straus, S., Wells, G., Pham, B., & Hutton, B. (2021) · BMC Medical Research Methodology · doi:10.1186/s12874-021-01451-2 · Cited by 104 · cited 1×
“Several approaches have been developed that use machine learning (ML) to automate or semi-automate screening [1, 6].”
Methodvan de Schoot, R., Sijbrandij, M., Depaoli, S., Winter, S. D., Olff, M., & van Loey, N. E. (2018) · Multivariate Behavioral Research · doi:10.1080/00273171.2017.1412293 · Cited by 85
Preventing harm from non-conscious bias in medical generative AI
Hastings, J. (2024) · The Lancet Digital Health · doi:10.1016/s2589-7500(23)00246-7 · Cited by 60
Self-citationClark, J., McFarlane, C., Cleo, G., Ishikawa Ramos, C., & Marshall, S. (2021) · JMIR Medical Education · doi:10.2196/24418 · Cited by 54 · cited 1×
“These approaches have been found to lead to a considerable reduction in the time taken to complete systematic reviews [15].”
BackgroundOverlap in meaning is a stronger predictor of semantic activation in GPT-3 than in humans
Digutsch, J., & Kosinski, M. (2023) · Scientific Reports · doi:10.1038/s41598-023-32248-6 · Cited by 49
Grounding Language Models to Images for Multimodal Inputs and Outputs
Koh, J. Y., Salakhutdinov, R., & Fried, D. (2023) · arXiv · doi:10.48550/arxiv.2301.13823 · Cited by 38
Meijboom, R. W., Gardarsdottir, H., Egberts, T. C. G., & Giezen, T. J. (2022) · BioDrugs · doi:10.1007/s40259-021-00508-4 · Cited by 18
Cited by
Dennstädt, F., Hastings, J., Putora, P. M., Schmerder, M., & Cihoric, N. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01476-7 · Cited by 144
Self-citationAutomation of Systematic Reviews with Large Language Models
Cao, C., Arora, R., Cento, P., Budak, A., Manta, K., Farahani, E., Cecere, M., Selemon, A., Sang, J., Gong, L. X., et al. (2025) · medRxiv · doi:10.1101/2025.06.13.25329541 · Cited by 33
Galli, C., Gavrilova, A. V., & Calciolari, E. (2025) · Information · doi:10.3390/info16050378 · Cited by 36
ASReview LAB v.2: Open-source text screening with multiple agents and a crowd of experts
de Bruin, J., Lombaers, P., Kaandorp, C., Teijema, J., van der Kuil, T., Yazan, B., Dong, A., & van de Schoot, R. (2025) · Patterns · doi:10.1016/j.patter.2025.101318 · Cited by 27
Novel AI applications in systematic review: gPT-4 assisted data extraction, analysis, review of bias
Kim, J. K., Chua, M. E., Li, T. G., Rickard, M., & Lorenzo, A. J. (2025) · BMJ Evidence-Based Medicine · doi:10.1136/bmjebm-2024-113066 · Cited by 11
Metadata
- Authors
- Dennstädt, F., Zink, J., Putora, P. M., Hastings, J., & Cihoric, N.
- Venue
- Systematic Reviews
- Published
- 2024-06-15
- Volume
- 13
- Issue
- 1
- Pages
- 158-158
- ISSN
- 2046-4053 (ISSN-L)
- OpenAlex
- W4399702760
- Cited by
- 145
- References
- 35
- FWCI
- 40.75
- Type
- journal article
- Language
- en
- Open access
- gold
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.
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.