[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127716-en":3,"doc-seo-127716-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},127716,962084928432,"Emma Wilson","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Fine-tuning GPT-3 for machine learning electronic and functional properties of organic molecules","Fine-tuning GPT-3 for the prediction of electronic and functional properties of organic molecules is systematically evaluated. The study shows that fine-tuned models capture chemically meaningful patterns, differentiate subtle structural differences, and maintain robust predictive performance across molecular property tasks. Particular emphasis is placed on resilience to information loss from missing atoms or chemical groups and to noise introduced by random atomic-identity alterations. Challenges and limitations of GPT-3 for molecular machine-learning are discussed, alongside directions for future improvements.","University of Birmingham  \nFine-tuning GPT-3 for machine learning electronic and functional properties of organic molecules  \nXie, Zikai; Evangelopoulos, Xenophon; Omar, Ömer; Troisi, Alessandro; Cooper, Andrew I. ; Chen, Linjiang  \nDOI:  \n10.26434/chemrxiv-2023-h02j4  \nLicense:  \nCreative Commons: Attribution-NonCommercial-NoDerivs (CC BY-NC-ND)  \nDocument Version  \nOther version  \nCitation for published version (Harvard):  \nXie, Z, Evangelopoulos, X, Omar, Ö, Troisi, A, Cooper, AI & Chen, L 2023 'Fine-tuning GPT-3 for machine learning electronic and functional properties of organic molecules' ChemRxiv. [https://doi.org/10.26434/chemrxiv-](https://doi.org/10.26434/chemrxiv-)[ ](https://doi.org/10.26434/chemrxiv-)[2023-h02j4](2023-h02j4)  \nLink to publication on Research at Birmingham portal  \nGeneral rights  \nUnless a licence is specified above, all rights (including copyright and moral rights) in this document are retained by the authors and/or the copyright holders. The express permission of the copyright holder must be obtained for any use of this material other than for purposes permitted by law.  \n•Users may freely distribute the URL that is used to identify this publication.  \n•Users may download and/or print one copy of the publication from the University of Birmingham research portal for the purpose of private study or non-commercial research.  \n•User may use extracts from the document in line with the concept of ‘fair dealing’ under the Copyright, Designs and Patents Act 1988 (?)  \n•Users may not further distribute the material nor use it for the purposes of commercial gain.  \nWhere a licence is displayed above, please note the terms and conditions of the licence govern your use of this document.  \nWhen citing, please reference the published version.  \nTake down policy  \nWhile the University of Birmingham exercises care and attention in making items available there are rare occasions when an item has been uploaded in error or has been deemed to be commercially or otherwise sensitive.  \nIf you believe that this is the case for this document, [please contact UBIRA@lists.bham.ac.uk](please contact UBIRA@lists.bham.ac.uk) providing details and we will remove access to the work immediately and investigate.  \nDownload date: 05. Aug. 2026  \nFine-tuning GPT-3 for machine learning electronic and functional properties of organic molecules  \nZikai Xie,a Xenophon Evangelopoulos,a Ömer H. Omar,b Alessandro Troisi,b Andrew I. Cooper,*a and Linjiang Chen *c  \na Leverhulme Research Centre for Functional Materials Design, Materials Innovation Factory and Department of Chemistry, University of Liverpool, Liverpool, L7 3NY, UK.  \nb Department of Chemistry, University of Liverpool, Liverpool, L69 3BX, UK.  \nc School of Chemistry and School of Computer Science, University of Birmingham, Birmingham, B15 2TT, UK.  \n* Corresponding authors: [aicooper@liverpool.ac.uk](aicooper@liverpool.ac.uk) (A.I.C.), [l.j.chen@bham.ac.uk](l.j.chen@bham.ac.uk) (L.C.)  \nAbstract  \nWe evaluate the effectiveness of fine-tuning GPT-3 for the prediction of electronic and functional properties of organic molecules. Our findings show that fine-tuned GPT-3 can successfully identify and distinguish between chemically meaningful patterns, and discern subtle differences among them, exhibiting robust predictive performance for the prediction of molecular properties. We focus on assessing the fine-tuned models' resilience to information loss, resulting from the absence of atoms or chemical groups, and to noise that we introduce via random alterations in atomic identities. We discuss the challenges and limitations inherent to the use of GPT-3 in molecular machine-learning tasks and suggest potential directions for future research and improvements to address these issues.  \n[https://doi.org/10.26434/chemrxiv-2023-h02j4](https://doi.org/10.26434/chemrxiv-2023-h02j4 ORCID:)[ ORCID:](https://doi.org/10.26434/chemrxiv-2023-h02j4 ORCID:) [https://orcid.org/0000-0002-0382-5863","cbCaigYPnwa4fj5c","https://ap.wps.com/l/cbCaigYPnwa4fj5c","pdf",789921,1,16,"English","en",105,"# Introduction\n## Motivation for using machine learning and large language models in chemistry\n## Role of GPT-3/4 and the need for fine-tuning","[{\"question\":\"What is evaluated in this work about GPT-3?\",\"answer\":\"The work evaluates how effective fine-tuning GPT-3 is for predicting electronic and functional properties of organic molecules.\"},{\"question\":\"How do fine-tuned GPT-3 models perform on molecular property prediction?\",\"answer\":\"They can identify and distinguish chemically meaningful patterns, discern subtle differences, and deliver robust predictive performance.\"},{\"question\":\"What robustness tests are applied to the fine-tuned models?\",\"answer\":\"The study tests resilience to information loss from absent atoms or chemical groups and to noise created by random changes in atomic identities.\"}]","Fine-tuning GPT-3 for machine learning electronic and functional properties of organic molecules | PDF",1785941153,40,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"fine-tuning-gpt-3-for-machine-learning-electronic-and-functional-properties-of-organic-molecules","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/fine-tuning-gpt-3-for-machine-learning-electronic-and-functional-properties-of-organic-molecules/127716/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What is evaluated in this work about GPT-3?","Question",{"text":76,"@type":77},"The work evaluates how effective fine-tuning GPT-3 is for predicting electronic and functional properties of organic molecules.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How do fine-tuned GPT-3 models perform on molecular property prediction?",{"text":81,"@type":77},"They can identify and distinguish chemically meaningful patterns, discern subtle differences, and deliver robust predictive performance.",{"name":83,"@type":74,"acceptedAnswer":84},"What robustness tests are applied to the fine-tuned models?",{"text":85,"@type":77},"The study tests resilience to information loss from absent atoms or chemical groups and to noise created by random changes in atomic identities.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":29,"slug":119},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]