{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:43:54Z","timestamp":1791305034871,"version":"4.3.1"},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T00:00:00Z","timestamp":1733875200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0"},{"start":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T00:00:00Z","timestamp":1733875200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Drug Saf"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s40264-024-01499-1","type":"journal-article","created":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T16:34:21Z","timestamp":1733934861000},"page":"287-303","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Performance and Reproducibility of Large Language Models in Named Entity Recognition: Considerations for the Use in Controlled Environments"],"prefix":"10.1007","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5494-3499","authenticated-orcid":false,"given":"J\u00fcrgen","family":"Dietrich","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andr\u00e9","family":"Hollstein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,11]]},"reference":[{"key":"1499_CR1","doi-asserted-by":"crossref","unstructured":"Mak K-K, Wong Y-H, Pichika MR. Artificial intelligence in drug discovery and development. Drug Discov Eval Saf Pharmacokinet Assays. 2023:1\u201338.","DOI":"10.1007\/978-3-030-73317-9_92-1"},{"issue":"9","key":"1499_CR2","doi-asserted-by":"publisher","first-page":"949","DOI":"10.1080\/17460441.2021.1909567","volume":"16","author":"J Jim\u00e9nez-Luna","year":"2021","unstructured":"Jim\u00e9nez-Luna J, Grisoni F, Weskamp N, Schneider G. Artificial intelligence in drug discovery: recent advances and future perspectives. Expert Opin Drug Discov. 2021;16(9):949\u201359.","journal-title":"Expert Opin Drug Discov"},{"issue":"7","key":"1499_CR3","doi-asserted-by":"publisher","first-page":"192","DOI":"10.9734\/jerr\/2023\/v25i7952","volume":"25","author":"S Nasnodkar","year":"2023","unstructured":"Nasnodkar S, Cinar B, Ness S. Artificial intelligence in toxicology and pharmacology. J Eng Res Rep. 2023;25(7):192\u2013206.","journal-title":"J Eng Res Rep."},{"issue":"8","key":"1499_CR4","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1016\/j.tips.2019.05.005","volume":"40","author":"S Harrer","year":"2019","unstructured":"Harrer S, Shah P, Antony B, Hu J. Artificial intelligence for clinical trial design. Trends Pharmacol Sci. 2019;40(8):577\u201391.","journal-title":"Trends Pharmacol Sci"},{"issue":"11","key":"1499_CR5","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1001\/jama.2020.1039","volume":"323","author":"DC Angus","year":"2020","unstructured":"Angus DC. Randomized clinical trials of artificial intelligence. JAMA. 2020;323(11):1043\u20135.","journal-title":"JAMA"},{"issue":"4","key":"1499_CR6","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1016\/j.tibtech.2022.08.007","volume":"41","author":"AS Rathore","year":"2023","unstructured":"Rathore AS, Nikita S, Thakur G, Mishra S. Artificial intelligence and machine learning applications in biopharmaceutical manufacturing. Trends Biotechnol. 2023;41(4):497\u2013510.","journal-title":"Trends Biotechnol"},{"key":"1499_CR7","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/s40290-018-0251-9","volume":"32","author":"D Abatemarco","year":"2018","unstructured":"Abatemarco D, Perera S, Bao SH, Desai S, Assuncao B, Tetarenko N, et al. Training augmented intelligent capabilities for pharmacovigilance: applying deep-learning approaches to individual case safety report processing. Pharm Med. 2018;32:391\u2013401.","journal-title":"Pharm Med."},{"issue":"8","key":"1499_CR8","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1007\/s40264-023-01315-2","volume":"46","author":"H Wang","year":"2023","unstructured":"Wang H, Ding YJ, Luo Y. Future of ChatGPT in pharmacovigilance. Drug Saf. 2023;46(8):711\u20133.","journal-title":"Drug Saf"},{"key":"1499_CR9","unstructured":"Ethics and governance of artificial intelligence for health\u2014who guide. 2021. https:\/\/iris.who.int\/bitstream\/handle\/10665\/341996\/9789240029200-eng.pdf. Accessed 29 July 2024."},{"issue":"4","key":"1499_CR10","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1002\/cpt.1255","volume":"105","author":"J Schmider","year":"2019","unstructured":"Schmider J, Kumar K, LaForest C, Swankoski B, Naim K, Caubel PM. Innovation in pharmacovigilance: use of artificial intelligence in adverse event case processing. Clin Pharmacol Ther. 2019;105(4):954\u201361.","journal-title":"Clin Pharmacol Ther"},{"key":"1499_CR11","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/s40290-019-00320-0","volume":"34","author":"R Ghosh","year":"2020","unstructured":"Ghosh R, Kempf D, Pufko A, Barrios Martinez LF, Davis CM, Sethi S. Automation opportunities in pharmacovigilance: an industry survey. Pharm Med. 2020;34:7\u201318.","journal-title":"Pharm Med."},{"issue":"5","key":"1499_CR12","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1007\/s40264-022-01164-5","volume":"45","author":"R Kassekert","year":"2022","unstructured":"Kassekert R, Grabowski N, Lorenz D, Schaffer C, Kempf D, Roy P, et al. Industry perspective on artificial intelligence\/machine learning in pharmacovigilance. Drug Saf. 2022;45(5):439\u201348.","journal-title":"Drug Saf"},{"key":"1499_CR13","unstructured":"Proposed regulatory framework for modifications to artificial intelligence\/machine learning (AI\/ML)-based software as a medical device (SaMD)\u2014discussion paper and request for Feedbac. 2019. https:\/\/www.fda.gov\/media\/122535\/download. Accessed 26 Feb 2024."},{"key":"1499_CR14","unstructured":"Informal innovation network horizon scanning assessment report\u2014artificial intelligence. 2021. https:\/\/www.icmra.info\/drupal\/sites\/default\/files\/2021-08\/horizon_scanning_report_artificial_intelligence.pdf. Accessed 29 July 2024."},{"key":"1499_CR15","unstructured":"Medical device software: considerations for device and risk characterization, IMDRF\/SaMD WG\/N81 DRAFT: 2024. 2024. https:\/\/www.imdrf.org\/sites\/default\/files\/2024-02\/IMDRFSaMD%20WGN81%20DRAFT%202024%2C%20Medical%20Device%20Software%20Considerations%20for%20Device%20and%20Risk%20Characterization%20-%20final%20draft.pdf. Accessed 29 June 2024."},{"key":"1499_CR16","unstructured":"Reflection paper on the use of Artificial Intelligence (AI) in the medicinal product lifecycle (Draft). 2023. https:\/\/www.ema.europa.eu\/en\/documents\/scientific-guideline\/draft-reflection-paper-use-artificial-intelligence-ai-medicinal-product-lifecycle_en.pdf. Accessed 29 July 2024."},{"key":"1499_CR17","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s40264-020-01030-2","volume":"44","author":"K Huysentruyt","year":"2021","unstructured":"Huysentruyt K, Kjoersvik O, Dobracki P, Savage E, Mishalov E, Cherry M, et al. Validating intelligent automation systems in pharmacovigilance: insights from good manufacturing practices. Drug Saf. 2021;44:261\u201372.","journal-title":"Drug Saf"},{"key":"1499_CR18","unstructured":"Developing a software precertification program: a working model v1.0 2019. https:\/\/www.fda.gov\/media\/119722\/download. Accessed 26 Feb 2024."},{"issue":"5","key":"1499_CR19","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1007\/s40264-022-01176-1","volume":"45","author":"B Kompa","year":"2022","unstructured":"Kompa B, Hakim JB, Palepu A, Kompa KG, Smith M, Bain PA, et al. Artificial intelligence based on machine learning in pharmacovigilance: a scoping review. Drug Saf. 2022;45(5):477\u201391.","journal-title":"Drug Saf"},{"issue":"2","key":"1499_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.hlpt.2023.100743","volume":"12","author":"A Bate","year":"2023","unstructured":"Bate A, Stegmann J-U. Artificial intelligence and pharmacovigilance: what is happening, what could happen and what should happen? Health Policy Technol. 2023;12(2): 100743.","journal-title":"Health Policy Technol."},{"key":"1499_CR21","unstructured":"Guideline on process validation for finished products\u2014information and data to be provided in regulatory submissions. 2016. https:\/\/www.ema.europa.eu\/en\/documents\/scientific-guideline\/guideline-process-validation-finished-products-information-and-data-be-provided-regulatory-submissions-revision-1_en.pdf. Accessed 01 Feb 2024."},{"key":"1499_CR22","unstructured":"Albertoni R, Colantonio S, Skrzypczy\u0144ski P, Stefanowski J. Reproducibility of machine learning: Terminology, recommendations and open issues. 2023. arXiv:230212691."},{"key":"1499_CR23","unstructured":"Guidance for Industry Process Validation: General Principles and Practices. 2011. https:\/\/www.fda.gov\/files\/drugs\/published\/Process-Validation--General-Principles-and-Practices.pdf. Accessed 01 Feb 2024."},{"issue":"4","key":"1499_CR24","first-page":"33","volume":"18","author":"P Katz","year":"2012","unstructured":"Katz P, Campbell C. FDA 2011 process validation guidance: process validation revisited. J Valid Technol. 2012;18(4):33.","journal-title":"J Valid Technol."},{"issue":"140","key":"1499_CR25","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, et al. Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res. 2020;21(140):1\u201367.","journal-title":"J Mach Learn Res"},{"key":"1499_CR26","unstructured":"Hugging Face T5 V4.24.0. https:\/\/www.huggingface.co\/docs\/transformers\/model_doc\/t5#transformers.T5Model. Accessed 10 Nov 2023."},{"key":"1499_CR27","doi-asserted-by":"crossref","unstructured":"Wadhwa S, Amir S, Wallace BC. Revisiting relation extraction in the era of large language models. In: Proceedings of the conference association for computational linguistics meeting; 2023: NIH public access; 2023. p. 15566.","DOI":"10.18653\/v1\/2023.acl-long.868"},{"issue":"5","key":"1499_CR28","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1016\/j.jbi.2012.04.008","volume":"45","author":"H Gurulingappa","year":"2012","unstructured":"Gurulingappa H, Rajput AM, Roberts A, Fluck J, Hofmann-Apitius M, Toldo L. Development of a benchmark corpus to support the automatic extraction of drug-related adverse effects from medical case reports. J Biomed Inform. 2012;45(5):885\u201392.","journal-title":"J Biomed Inform"},{"key":"1499_CR29","doi-asserted-by":"crossref","unstructured":"Hu Y, Chen Q, Du J, Peng X, Keloth VK, Zuo X, et al. Improving large language models for clinical named entity recognition via prompt engineering. J Am Med Inform Assoc. 2024.","DOI":"10.1093\/jamia\/ocad259"},{"issue":"3","key":"1499_CR30","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0300919","volume":"19","author":"Y Li","year":"2024","unstructured":"Li Y, Li J, He J, Tao C. AE-GPT: using large language models to extract adverse events from surveillance reports-a use case with influenza vaccine adverse events. PLoS ONE. 2024;19(3): e0300919.","journal-title":"PLoS ONE"},{"key":"1499_CR31","doi-asserted-by":"crossref","unstructured":"Raval S, Sedghamiz H, Santus E, Alhanai T, Ghassemi M, Chersoni E. Exploring a unified sequence-to-sequence transformer for medical product safety monitoring in social media. 2021 November; Punta Cana, Dominican Republic: Association for Computational Linguistics; 2021. pp. 3534\u201346.","DOI":"10.18653\/v1\/2021.findings-emnlp.300"},{"issue":"8","key":"1499_CR32","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1007\/s40264-023-01322-3","volume":"46","author":"J Dietrich","year":"2023","unstructured":"Dietrich J, Kazzer P. Provision and characterization of a corpus for pharmaceutical, biomedical named entity recognition for pharmacovigilance: evaluation of language registers and training data sufficiency. Drug Saf. 2023;46(8):765\u201379. https:\/\/doi.org\/10.1007\/s40264-023-01322-3.","journal-title":"Drug Saf"},{"key":"1499_CR33","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, et al. Language models are few-shot learners. Adv Neural Inf Process Syst. 2020;33:1877\u2013901.","journal-title":"Adv Neural Inf Process Syst"},{"key":"1499_CR34","doi-asserted-by":"crossref","unstructured":"Lu Y, Bartolo M, Moore A, Riedel S, Stenetorp P. Fantastically ordered prompts and where to find them: overcoming few-shot prompt order sensitivity. 2021. arXiv:210408786.","DOI":"10.18653\/v1\/2022.acl-long.556"},{"key":"1499_CR35","doi-asserted-by":"crossref","unstructured":"Rubin O, Herzig J, Berant J. Learning to retrieve prompts for in-context learning. 2021. arXiv:211208633.","DOI":"10.18653\/v1\/2022.naacl-main.191"},{"key":"1499_CR36","unstructured":"Achiam J, Adler S, Agarwal S, Ahmad L, Akkaya I, Aleman FL, et al. Gpt-4 technical report. 2023. arXiv:230308774."},{"key":"1499_CR37","unstructured":"OpenAI Platform. https:\/\/platform.openai.com\/docs\/models. Accessed 05 Dec 2023."},{"key":"1499_CR38","unstructured":"Notus 7B v1. https:\/\/huggingface.co\/argilla\/notus-7b-v1. Accessed 15 Oct 2023."},{"key":"1499_CR39","unstructured":"Meditron-7B-v1.0. https:\/\/huggingface.co\/epfl-llm\/meditron-7b. Accessed 15 Oct 2023."},{"key":"1499_CR40","unstructured":"Zephyr 7B \u03b2. https:\/\/huggingface.co\/HuggingFaceH4\/zephyr-7b-beta. Accessed 15 Oct 2023."},{"key":"1499_CR41","unstructured":"Llama 2 13B. https:\/\/huggingface.co\/meta-llama\/Llama-2-13b-hf. Accessed 15 Oct 23."},{"key":"1499_CR42","unstructured":"Llama-2-7B-32K-Instruct. https:\/\/huggingface.co\/togethercomputer\/Llama-2-7B-32K-Instruct. Accessed 15 Oct 2023."},{"issue":"10","key":"1499_CR43","doi-asserted-by":"publisher","first-page":"1274","DOI":"10.1093\/jamia\/ocy114","volume":"25","author":"A Sarker","year":"2018","unstructured":"Sarker A, Belousov M, Friedrichs J, Hakala K, Kiritchenko S, Mehryary F, et al. Data and systems for medication-related text classification and concept normalization from Twitter: insights from the Social Media Mining for Health (SMM4H)-2017 shared task. J Am Med Inform Assoc. 2018;25(10):1274\u201383.","journal-title":"J Am Med Inform Assoc"},{"key":"1499_CR44","unstructured":"New drug approvals archive for 2010\u20132021. https:\/\/www.drugs.com\/newdrugs-archive\/2021.html. Accessed 30 Sept 2021"},{"key":"1499_CR45","unstructured":"Schulhoff S, Ilie M, Balepur N, Kahadze K, Liu A, Si C, et al. The prompt report: a systematic survey of prompting techniques. arXiv:240606608. 2024."},{"key":"1499_CR46","unstructured":"Prompt engineering guide. https:\/\/www.promptingguide.ai\/. Accessed 15 June 2024."},{"key":"1499_CR47","unstructured":"Anadkat S. How to make your completions outputs consistent with the new seed parameter. https:\/\/cookbook.openai.com\/examples\/reproducible_outputs_with_the_seed_parameter. Accessed 01 Mar 2024."},{"key":"1499_CR48","unstructured":"Wolf EBaCFaNHaSHaNLaNRaOSaLTaT. Open LLM Leaderboard. 2023. https:\/\/huggingface.co\/spaces\/HuggingFaceH4\/open_llm_leaderboard. Accessed 05 Dec 2023."},{"key":"1499_CR49","doi-asserted-by":"crossref","unstructured":"Rebedea T, Dinu R, Sreedhar MN, Parisien C, Cohen J. NeMo guardrails: a toolkit for controllable and safe LLM applications with programmable rails. In: Proceedings of the 2023 conference on empirical methods in natural language processing: system demonstrations; 2023; 2023. pp. 431\u201345.","DOI":"10.18653\/v1\/2023.emnlp-demo.40"},{"key":"1499_CR50","unstructured":"A guidance language for controlling large language models. https:\/\/github.com\/guidance-ai\/guidance. Accessed 01 Mar 2024."},{"key":"1499_CR51","unstructured":"Dettmers T, Pagnoni A, Holtzman A, Zettlemoyer L. QLoRA: efficient finetuning of quantized llms. Adv Neural Inf Process Syst. 2024;36."},{"key":"1499_CR52","unstructured":"X\u2014LLM: cutting edge & easy LLM finetuning. https:\/\/github.com\/BobaZooba\/xllm. Accessed 20 Dec 2023."},{"issue":"6","key":"1499_CR53","first-page":"7","volume":"3","author":"R Taori","year":"2023","unstructured":"Taori R, Gulrajani I, Zhang T, Dubois Y, Li X, Guestrin C, et al. Alpaca: a strong, replicable instruction-following model. Stanford Center Res Found Models. 2023;3(6):7.","journal-title":"Stanford Center Res Found Models."},{"key":"1499_CR54","unstructured":"Touvron H, Martin L, Stone K, Albert P, Almahairi A, Babaei Y, et al. Llama 2: open foundation and fine-tuned chat models. 2023. arXiv:230709288."},{"key":"1499_CR55","unstructured":"Tunstall L, Beeching E, Lambert N, Rajani N, Rasul K, Belkada Y, et al. Zephyr: direct distillation of lm alignment. 2023. arXiv:231016944."},{"key":"1499_CR56","unstructured":"Kaplan J, McCandlish S, Henighan T, Brown TB, Chess B, Child R, et al. Scaling laws for neural language models. 2020. arXiv:200108361."},{"key":"1499_CR57","doi-asserted-by":"crossref","unstructured":"Kirstain Y, Lewis P, Riedel S, Levy O. A few more examples may be worth billions of parameters. 2021. arXiv:211004374.","DOI":"10.18653\/v1\/2022.findings-emnlp.72"},{"key":"1499_CR58","unstructured":"Jiang AQ, Sablayrolles A, Mensch A, Bamford C, Chaplot DS, Casas Ddl, et al. Mistral 7B. 2023. arXiv:231006825."},{"key":"1499_CR59","unstructured":"Rafailov R, Sharma A, Mitchell E, Manning CD, Ermon S, Finn C. Direct preference optimization: your language model is secretly a reward model. Adv Neural Inf Process Syst. 2024;36."},{"key":"1499_CR60","unstructured":"Zhou C, Liu P, Xu P, Iyer S, Sun J, Mao Y, et al. Lima: Less is more for alignment. Adv Neural Inf Process Syst. 2024;36."},{"key":"1499_CR61","unstructured":"Kapoor S, Bommasani R, Klyman K, Longpre S, Ramaswami A, Cihon P, et al. On the societal impact of open foundation models. 2024."}],"container-title":["Drug Safety"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40264-024-01499-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40264-024-01499-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40264-024-01499-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T01:47:00Z","timestamp":1757123220000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40264-024-01499-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,11]]},"references-count":61,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["1499"],"URL":"https:\/\/doi.org\/10.1007\/s40264-024-01499-1","relation":{},"ISSN":["0114-5916","1179-1942"],"issn-type":[{"value":"0114-5916","type":"print"},{"value":"1179-1942","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,11]]},"assertion":[{"value":"11 November 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 2024","order":2,"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":"Funding"}},{"value":"J\u00fcrgen Dietrich holds shares in Bayer AG. J\u00fcrgen Dietrich is a full-time employee of Bayer AG. Andr\u00e9 Hollstein holds shares in Bayer AG. Andr\u00e9 Hollstein is a full-time employee of Bayer AG. J\u00fcrgen Dietrich and Andr\u00e9 Hollstein have no conflict of interest that are directly relevant to the content of this experiment. The views expressed in this paper are those of the authors and do not necessarily reflect the official policy or position of Bayer AG.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The dataset used is publicly available in publication [] under Supplementary file 1,","order":7,"name":"Ethics","group":{"name":"EthicsHeading","label":"Availability of data and material"}},{"value":"The code used for this experiment is not provided, as a patent is pending.","order":8,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}},{"value":"J\u00fcrgen Dietrich and Andr\u00e9 Hollstein were involved in the conception and design of the experiments and result interpretation. Andr\u00e9 Hollstein was responsible for code generation of guidance AI implementation and the execution of few-shot experiments, J\u00fcrgen Dietrich was responsible for the rest of the code generation tasks and the execution of cross-validation and LLM finetuning experiments. All authors contributed to the interpretation of the data analysis results and assisted with the concept and draft revisions of the manuscript. All authors reviewed and approved the final manuscript and accept full responsibility for its overall content.","order":9,"name":"Ethics","group":{"name":"EthicsHeading","label":"Authors\u2019 contributions"}}]}}