{"id":"https://openalex.org/W4400947724","doi":"https://doi.org/10.1145/3672919.3672971","title":"ChemGen: Towards Understanding First-Principles Calculation Code Generation Based on Large Language Models","display_name":"ChemGen: Towards Understanding First-Principles Calculation Code Generation Based on Large Language Models","publication_year":2024,"publication_date":"2024-03-01","ids":{"openalex":"https://openalex.org/W4400947724","doi":"https://doi.org/10.1145/3672919.3672971"},"language":"en","primary_location":{"id":"doi:10.1145/3672919.3672971","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3672919.3672971","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 3rd International Conference on Cyber Security, Artificial Intelligence and Digital Economy","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052536033","display_name":"Peng Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peng Gao","raw_affiliation_strings":["School of Software Engineering, University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0009-0001-4251-6596","affiliations":[{"raw_affiliation_string":"School of Software Engineering, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Feng Qiu","orcid":"https://orcid.org/0009-0005-2809-5720"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Qiu","raw_affiliation_strings":["School of Software Engineering, University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0009-0005-2809-5720","affiliations":[{"raw_affiliation_string":"School of Software Engineering, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082542143","display_name":"Baojian Hua","orcid":"https://orcid.org/0000-0003-4434-2355"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baojian Hua","raw_affiliation_strings":["School of Software Engineering, University of Science and Technology of China, China and \rSuzhou Institute for Advanced Research, University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0003-4434-2355","affiliations":[{"raw_affiliation_string":"School of Software Engineering, University of Science and Technology of China, China and \rSuzhou Institute for Advanced Research, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I308837","https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052536033"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.2266,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46851662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"281","last_page":"287"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9749000072479248,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10911","display_name":"Chemical Synthesis and Analysis","score":0.9710000157356262,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7524484395980835},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.6042509078979492},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.5819700360298157},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5314679741859436},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3209994435310364},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08310315012931824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7524484395980835},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6042509078979492},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5819700360298157},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5314679741859436},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3209994435310364},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08310315012931824},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3672919.3672971","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3672919.3672971","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 3rd International Conference on Cyber Security, Artificial Intelligence and Digital Economy","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1964962870","https://openalex.org/W2030976617","https://openalex.org/W2083222334","https://openalex.org/W3011574394","https://openalex.org/W3030008171","https://openalex.org/W3088409176","https://openalex.org/W3121692464","https://openalex.org/W3207553988","https://openalex.org/W4211263275","https://openalex.org/W4312438588","https://openalex.org/W4319996831","https://openalex.org/W4391924034"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2163672025","https://openalex.org/W2258184894","https://openalex.org/W2048831961","https://openalex.org/W1606349578"],"abstract_inverted_index":{"First-principles":[0],"calculation":[1],"software,":[2],"grounded":[3],"in":[4,10,64,115],"quantum":[5],"chemistry":[6],"theories,":[7],"is":[8],"indispensable":[9],"scientific":[11],"research.":[12],"However,":[13],"the":[14,20,113,121,124,129,137,140,146,149],"development":[15],"of":[16,22,112,120,128,139,148],"such":[17],"software":[18],"requires":[19],"amalgamation":[21],"multidisciplinary":[23],"knowledge,":[24],"posing":[25],"a":[26,58,76],"significant":[27],"challenge":[28],"to":[29,35,62],"developers.":[30],"We":[31],"propose":[32],"an":[33],"approach":[34],"utilize":[36],"large":[37],"language":[38],"models":[39,104],"(LLMs)":[40],"for":[41,45,69,87,110,118],"automatically":[42],"generating":[43,65],"code":[44,68,83,109,131],"first-principles":[46,70,88],"calculations.":[47,71,89],"Building":[48],"on":[49],"this":[50],"concept,":[51],"we":[52,73],"have":[53,74],"designed":[54],"and":[55,66,100],"implemented":[56],"ChemGen,":[57],"fully":[59],"automated":[60],"framework":[61],"assist":[63],"evaluating":[67],"Meanwhile,":[72],"developed":[75],"benchmark":[77],"named":[78],"ChemEval,":[79],"which":[80],"includes":[81],"24":[82],"generation":[84,142],"tasks":[85,114],"tailored":[86],"Our":[90],"experiments,":[91],"conducted":[92],"using":[93],"three":[94],"leading":[95],"LLMs\u2014GPT-3.5":[96],"Turbo,":[97],"Gemini":[98],"Pro,":[99],"WizardCoder-Python-13B\u2014indicate":[101],"that":[102],"these":[103],"can":[105],"generate":[106],"functionally":[107],"correct":[108],"79.17%":[111],"ChemEval.":[116],"Additionally,":[117],"each":[119],"LLMs":[122],"used,":[123],"median":[125],"cyclomatic":[126],"complexity":[127],"generated":[130],"did":[132],"not":[133],"exceed":[134],"3.":[135],"Furthermore,":[136],"application":[138],"knowledge":[141],"prompting":[143],"technique":[144],"improves":[145],"accuracy":[147],"produced":[150],"code.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}