{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T08:23:48Z","timestamp":1769156628411,"version":"3.49.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T00:00:00Z","timestamp":1765929600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T00:00:00Z","timestamp":1769040000000},"content-version":"vor","delay-in-days":36,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"DOI":"10.1186\/s12859-025-06350-7","type":"journal-article","created":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T18:43:57Z","timestamp":1765997037000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SKiM-GPT: combining biomedical literature-based discovery with large language model hypothesis evaluation"],"prefix":"10.1186","volume":"27","author":[{"given":"Jack","family":"Freeman","sequence":"first","affiliation":[]},{"given":"Robert J.","family":"Millikin","sequence":"additional","affiliation":[]},{"given":"Leo","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Ishaan","family":"Sharma","sequence":"additional","affiliation":[]},{"given":"Bethany","family":"Moore","sequence":"additional","affiliation":[]},{"given":"Cannon","family":"Lock","sequence":"additional","affiliation":[]},{"given":"Kevin","family":"Shine George","sequence":"additional","affiliation":[]},{"given":"Aviral","family":"Bal","sequence":"additional","affiliation":[]},{"given":"Chitrasen","family":"Mohanty","sequence":"additional","affiliation":[]},{"given":"Ron","family":"Stewart","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,12,17]]},"reference":[{"key":"6350_CR1","doi-asserted-by":"publisher","unstructured":"Abdin M, Aneja J, Awadalla H, Awadallah A, Awan AA, Bach N, et al. Phi-3 technical report: A highly capable language model locally on your phone. arXiv preprint. 2024;arXiv:2404.14219. https:\/\/doi.org\/10.48550\/arXiv.2404.14219","DOI":"10.48550\/arXiv.2404.14219"},{"key":"6350_CR2","doi-asserted-by":"publisher","unstructured":"Anil R, Borgeaud S, Alayrac JB, Yu J, Soricut R, Schalkwyk J, et al. Gemini: A family of highly capable multimodal models. arXiv preprint. 2023;arXiv:2312.11805. https:\/\/doi.org\/10.48550\/arXiv.2312.11805","DOI":"10.48550\/arXiv.2312.11805"},{"key":"6350_CR3","doi-asserted-by":"publisher","DOI":"10.47852\/bonviewMEDIN52025348","author":"B Bhasuran","year":"2025","unstructured":"Bhasuran B, Murugesan G, Natarajan J. Literature-based discovery (LBD): Towards hypothesis generation and knowledge discovery in biomedical text mining. Medinformatics. 2025;2(4):241\u201355. https:\/\/doi.org\/10.47852\/bonviewMEDIN52025348","journal-title":"Medinformatics"},{"key":"6350_CR4","doi-asserted-by":"publisher","unstructured":"Cao H, An Z, Feng J, Xu K, Chen L, Zhao D. A step closer to comprehensive answers: Constrained multi-stage question decomposition with large language models. arXiv preprint. 2023;arXiv:2311.07491. https:\/\/doi.org\/10.48550\/arXiv.2311.07491","DOI":"10.48550\/arXiv.2311.07491"},{"issue":"6","key":"6350_CR5","doi-asserted-by":"publisher","first-page":"1205","DOI":"10.1007\/s12553-021-00605-y","volume":"11","author":"S Cheerkoot-Jalim","year":"2021","unstructured":"Cheerkoot-Jalim S, and Khedo KK. Literature-Based discovery approaches for Evidence-Based healthcare: A systematic review. Health Technol. 2021;11(6):1205\u201317. https:\/\/doi.org\/10.1007\/s12553-021-00605-y.","journal-title":"Health Technol"},{"key":"6350_CR6","doi-asserted-by":"publisher","unstructured":"Chen J, Lin H, Han X, Sun L. Benchmarking Large Language Models in Retrieval-Augmented Generation. Proceedings of the AAAI Conference on Artificial Intelligence 2024;38(16):17754\u201362. https:\/\/doi.org\/10.1609\/aaai.v38i16.29728","DOI":"10.1609\/aaai.v38i16.29728"},{"issue":"1","key":"6350_CR7","doi-asserted-by":"publisher","first-page":"3280","DOI":"10.1038\/s41467-025-56989-2","volume":"16","author":"Q Chen","year":"2025","unstructured":"Chen Q, Peng YHX, Xie Q, Jin Q, Gilson A, Singer MB, et al. Benchmarking large language models for biomedical natural language processing applications and recommendations. Nat Commun. 2025;16(1):3280. https:\/\/doi.org\/10.1038\/s41467-025-56989-2","journal-title":"Nat Commun"},{"issue":"4","key":"6350_CR8","doi-asserted-by":"publisher","first-page":"e1007617","DOI":"10.1371\/journal.pcbi.1007617","volume":"16","author":"Q Chen","year":"2020","unstructured":"Chen Q, Lee K, Kim SYS, Wei C-H, Lu Z. BioConceptVec: creating and evaluating Literature-Based biomedical concept embeddings on a large scale. PLoS Comput Biol. 2020;16(4):e1007617. https:\/\/doi.org\/10.1371\/journal.pcbi.1007617.","journal-title":"PLoS Comput Biol"},{"key":"6350_CR9","doi-asserted-by":"publisher","unstructured":"DeepSeek-AI, Guo D, Yang H, Zhang J, Song R, Zhang R, Xu R et al. DeepSeek-R1: incentivizing reasoning capability in LLMs via reinforcement Learning. arXiv preprint. 2025;arXiv:2501.12948. https:\/\/doi.org\/10.48550\/arXiv.2501.12948.","DOI":"10.48550\/arXiv.2501.12948"},{"issue":"1","key":"6350_CR10","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1186\/s12859-025-06159-4","volume":"26","author":"B Edelman","year":"2025","unstructured":"Edelman B, Skolnick J. Valsci: An open-source, self-hostable literature review utility for automated large-batch scientific claim verification using large Language models. BMC Bioinformatics. 2025;26(1):140. https:\/\/doi.org\/10.1186\/s12859-025-06159-4.","journal-title":"BMC Bioinformatics"},{"issue":"3","key":"6350_CR11","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1177\/001316447303300309","volume":"33","author":"JL Fleiss","year":"1973","unstructured":"Fleiss JL, and Cohen J. The equivalence of weighted kappa and the intraclass correlation coefficient as measures of reliability. Educ Psychol Meas. 1973;33(3):613\u201319. https:\/\/doi.org\/10.1177\/001316447303300309.","journal-title":"Educ Psychol Meas"},{"key":"6350_CR12","doi-asserted-by":"publisher","unstructured":"Gao Y, Xiong Y, Gao X, Jia K, Pan J, Bi Y, Dai Y, Sun J, Wang M, Wang H. Retrieval-Augmented Generation for Large Language Models: A Survey. arXiv. 2024;2312.10997 https:\/\/doi.org\/10.48550\/arXiv.2312.10997","DOI":"10.48550\/arXiv.2312.10997"},{"issue":"May","key":"6350_CR13","doi-asserted-by":"publisher","first-page":"103141","DOI":"10.1016\/j.jbi.2019.103141","volume":"93","author":"V Gopalakrishnan","year":"2019","unstructured":"Gopalakrishnan V, Jha K, Jin W, Zhang A. A survey on literature based discovery approaches in biomedical domain. J Biomed Inform. 2019;93:103141. https:\/\/doi.org\/10.1016\/j.jbi.2019.103141.","journal-title":"J Biomed Inform"},{"key":"6350_CR14","doi-asserted-by":"publisher","unstructured":"Gottweis J, Weng W-H, Daryin A, Tu T, Palepu A, Sirkovic P et al. Towards an AI co-scientist. arXiv preprint. 2025;arXiv:2502.18864. https:\/\/doi.org\/10.48550\/arXiv.2502.18864","DOI":"10.48550\/arXiv.2502.18864"},{"key":"6350_CR15","unstructured":"Hristovski D, Friedman C, Rindflesch TC, Peterlin B. Exploiting semantic relations for literature-based discovery. AMIA annual symposium proceedings. 2006;2006:349\u201353."},{"key":"6350_CR16","doi-asserted-by":"publisher","unstructured":"Hsieh CP, Sun S, Kriman S, Acharya S, Rekesh D, Jia F, et al. RULER: What\u2019s the real context size of your long-context language models? arXiv preprint. 2024;arXiv:2404.06654 https:\/\/doi.org\/10.48550\/arXiv.2404.06654","DOI":"10.48550\/arXiv.2404.06654"},{"key":"6350_CR17","doi-asserted-by":"publisher","unstructured":"Jin Q, Dhingra B, Liu Z, Cohen W, Lu X. PubMedQA: A dataset for biomedical research question answering. Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP). 2019;2019:2567\u201377. https:\/\/doi.org\/10.18653\/v1\/D19-1259","DOI":"10.18653\/v1\/D19-1259"},{"issue":"2","key":"6350_CR18","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.jcm.2016.02.012","volume":"15","author":"TK Koo","year":"2016","unstructured":"Koo TK, Li MY. A guideline of selecting and reporting intraclass correlation coefficients for reliability research. J Chiropr Med. 2016;15(2):155. https:\/\/doi.org\/10.1016\/j.jcm.2016.02.012.","journal-title":"J Chiropr Med"},{"key":"6350_CR19","unstructured":"Kuusisto F, Steill J, Kuang Z, Thomson J, Page D, Stewart R. A simple text mining approach for ranking pairwise associations in biomedical applications. AMIA summits on translational science proceedings. 2017;2017:166."},{"key":"6350_CR20","unstructured":"Lewis P, Perez E, Piktus A, Petroni F, Karpukhin V, Goyal N, et al. Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in neural information processing systems. 2020;33:9459\u201374."},{"key":"6350_CR21","doi-asserted-by":"publisher","unstructured":"Maynez J, Narayan S, Bohnet B, McDonald R. On faithfulness and factuality in abstractive summarization. arXiv preprint. 2020;arXiv:2005.00661. https:\/\/doi.org\/10.48550\/arXiv.2005.00661.","DOI":"10.48550\/arXiv.2005.00661"},{"issue":"1","key":"6350_CR22","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1186\/s12859-023-05539-y","volume":"24","author":"RJ Millikin","year":"2023","unstructured":"Millikin RJ, Raja K, Steill J, Lock C, Tu X, Ross I, et al. Serial KinderMiner (SKiM) discovers and annotates biomedical knowledge using co-occurrence and transformer models. BMC Bioinformatics. 2023;24(1). https:\/\/doi.org\/10.1186\/s12859-023-05539-y","journal-title":"BMC Bioinformatics"},{"key":"6350_CR23","doi-asserted-by":"publisher","unstructured":"Modarressi A, Deilamsalehy H, Dernoncourt F, Bui T, Rossi R, Yoon S, et al. NoLiMa: Long-context evaluation beyond literal matching. arXiv preprint. 2025;arXiv:2502.05167. https:\/\/doi.org\/10.48550\/arXiv.2502.05167","DOI":"10.48550\/arXiv.2502.05167"},{"key":"6350_CR24","doi-asserted-by":"publisher","unstructured":"OpenAI Team: Jaech A, Kalai A, Lerer A, Richardson A, El-Kishky A, et al. OpenAI o1 system card. arXiv preprint. 2024;arXiv:2412.16720 https:\/\/doi.org\/10.48550\/arXiv.2412.16720","DOI":"10.48550\/arXiv.2412.16720"},{"key":"6350_CR25","doi-asserted-by":"publisher","unstructured":"Pham DK, Vo BQ. Towards reliable medical question answering: Techniques and challenges in mitigating hallucinations in language models. arXiv preprint. 2024;arXiv:2408.13808. https:\/\/doi.org\/10.48550\/arXiv.2408.13808","DOI":"10.48550\/arXiv.2408.13808"},{"issue":"7","key":"6350_CR26","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1186\/s12859-017-1641-9","volume":"18","author":"J Preiss","year":"2017","unstructured":"Preiss J, Stevenson M. Quantifying and filtering knowledge generated by literature based discovery. BMC Bioinformatics. 2017;18(S7). https:\/\/doi.org\/10.1186\/s12859-017-1641-9.","journal-title":"BMC Bioinformatics"},{"issue":"9","key":"6350_CR27","doi-asserted-by":"publisher","first-page":"1553","DOI":"10.1093\/bioinformatics\/bty845","volume":"35","author":"S Pyysalo","year":"2019","unstructured":"Pyysalo S, Baker S, Ali I, Haselwimmer S, Shah T, Young A, et al. LION LBD: A literature-based discovery system for cancer biology. Bioinformatics. 2019;35(9):1553\u201361. https:\/\/doi.org\/10.1093\/bioinformatics\/bty845","journal-title":"Bioinf (Oxford England)"},{"key":"6350_CR28","doi-asserted-by":"publisher","unstructured":"Rein D, Hou BL, Stickland AC, Petty J, Pang RY, Dirani J, et al. GPQA: A graduate-level Google-proof Q&A benchmark. First Conference on Language Modeling. 2024. https:\/\/doi.org\/10.48550\/arXiv.2311.12022","DOI":"10.48550\/arXiv.2311.12022"},{"issue":"D1","key":"6350_CR29","doi-asserted-by":"publisher","first-page":"D20","DOI":"10.1093\/nar\/gkae979","volume":"53","author":"Eric W Sayers","year":"2025","unstructured":"Sayers EW, Beck J, Bolton EE, Brister JR, Chan J, Connor R, et al. Database resources of the National Center for Biotechnology Information in 2025. Nucleic Acids Research. 2025;53(D1):D20\u2013D9. https:\/\/doi.org\/10.1093\/nar\/gkae979","journal-title":"Nucleic Acids Res"},{"issue":"4","key":"6350_CR30","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1515\/jdis-2017-0019","volume":"2","author":"NR Smalheiser","year":"2017","unstructured":"Smalheiser NR. Rediscovering Don Swanson: The past, present and future of literature-based discovery. Journal of Data and Information Science. 2017;2(4):43\u201364. https:\/\/doi.org\/10.1515\/jdis-2017-0019","journal-title":"J Data Inform Sci (Warsaw Poland)"},{"issue":"1","key":"6350_CR31","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1186\/1471-2105-9-402","volume":"9","author":"S Sohn","year":"2008","unstructured":"Sohn S, Comeau DC, Kim W, Wilbur WJ. Abbreviation definition identification based on automatic precision estimates. BMC Bioinformatics. 2008;9(1):402. https:\/\/doi.org\/10.1186\/1471-2105-9-402.","journal-title":"BMC Bioinformatics"},{"issue":"4","key":"6350_CR32","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1002\/(SICI)1097-4571(198707)38:4<228::AID-ASI2>3.0.CO;2-G","volume":"38","author":"DR Swanson","year":"1987","unstructured":"Swanson DR. Two medical literatures that are logically but not bibliographically connected. Journal of the American Society for Information Science. 1987;38(4):228\u201333.","journal-title":"Journal of the American Society for Information Science"},{"key":"6350_CR33","doi-asserted-by":"publisher","unstructured":"Tonmoy SMTI, Zaman SMM, Jain V, Rani A, Rawte V, Chadha A, et al. A comprehensive survey of hallucination mitigation techniques in large language models. arXiv preprint. 2024;arXiv:2401.01313. https:\/\/doi.org\/10.48550\/arXiv.2401.01313","DOI":"10.48550\/arXiv.2401.01313"},{"issue":"13","key":"6350_CR34","doi-asserted-by":"publisher","first-page":"1658","DOI":"10.1093\/bioinformatics\/btm161","volume":"23","author":"VI Torvik","year":"2007","unstructured":"Torvik VI, Smalheiser NR. A quantitative model for linking two disparate sets of articles in MEDLINE. Bioinformatics. 2007;23(13):1658\u201365. https:\/\/doi.org\/10.1093\/bioinformatics\/btm161","journal-title":"Bioinformatics"},{"key":"6350_CR35","doi-asserted-by":"publisher","unstructured":"Tyagin I, Kulshrestha A, Sybrandt J, Matta K, Shtutman M, Safro I. Accelerating COVID-19 research with graph mining and transformer-based learning. Proceedings of the AAAI conference on artificial intelligence. 2022;36(11):12673\u20139. https:\/\/doi.org\/10.48550\/arXiv.2102.07631","DOI":"10.48550\/arXiv.2102.07631"},{"key":"6350_CR36","doi-asserted-by":"publisher","unstructured":"Tyagin I, Safro I. Dyport: Dynamic importance-based biomedical hypothesis generation benchmarking technique. BMC Bioinformatics. 2024;25(1). https:\/\/doi.org\/10.1186\/s12859-024-05812-8","DOI":"10.1186\/s12859-024-05812-8"},{"key":"6350_CR37","doi-asserted-by":"publisher","unstructured":"Wei CH, Lee K, Leaman R, Lu Z. Biomedical mention disambiguation using a deep learning approach. Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics. 2019:307\u201313. https:\/\/doi.org\/10.48550\/arXiv.1909.10416","DOI":"10.48550\/arXiv.1909.10416"},{"key":"6350_CR38","unstructured":"Wei J, Wang X, Schuurmans D, Bosma M, Xia F, Chi E, et al. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems. 2022;35:24824\u201337."},{"key":"6350_CR39","doi-asserted-by":"crossref","unstructured":"Yu Y, Ping W, Liu Z, Wang B, You J, Zhang C, et al. RankRAG: Unifying context ranking with retrieval-augmented generation in LLMs. Advances in Neural Information Processing Systems. 2024;37:121156\u201384.","DOI":"10.52202\/079017-3850"},{"key":"6350_CR40","doi-asserted-by":"publisher","unstructured":"Zhang Y, Chen X, Jin B, Wang S, Ji S, Wang W, et al. A comprehensive survey of scientific large language models and their applications in scientific discovery. arXiv preprint. 2024;arXiv:2406.10833. https:\/\/doi.org\/10.48550\/arXiv.2406.10833.","DOI":"10.48550\/arXiv.2406.10833"},{"key":"6350_CR41","doi-asserted-by":"publisher","unstructured":"Zhao WX, Zhou K, Li J, Tang T, Wang X, Hou Y, et al. A survey of large language models. arXiv preprint. 2023;arXiv:2303.18223. https:\/\/doi.org\/10.48550\/arXiv.2303.18223.","DOI":"10.48550\/arXiv.2303.18223"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-025-06350-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-025-06350-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-025-06350-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T16:17:03Z","timestamp":1769098623000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12859-025-06350-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,17]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["6350"],"URL":"https:\/\/doi.org\/10.1186\/s12859-025-06350-7","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,17]]},"assertion":[{"value":"29 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 December 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. This work analyzed publicly available biomedical abstracts and did not involve human participants.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable. The manuscript does not contain any individual person\u2019s data.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"16"}}