{"id":"https://openalex.org/W4403577809","doi":"https://doi.org/10.1145/3627673.3679874","title":"Application of Large Language Models in Chemistry Reaction Data Extraction and Cleaning","display_name":"Application of Large Language Models in Chemistry Reaction Data Extraction and Cleaning","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403577809","doi":"https://doi.org/10.1145/3627673.3679874"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679874","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679874","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3627673.3679874?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3627673.3679874?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101833672","display_name":"Xiaobao Huang","orcid":"https://orcid.org/0009-0002-1679-3888"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaobao Huang","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114337366","display_name":"Mihir Surve","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mihir Surve","raw_affiliation_strings":["University of Notre Dame, Notre Dame, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350537","display_name":"Yuhan Liu","orcid":"https://orcid.org/0000-0003-4793-5543"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuhan Liu","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101845761","display_name":"Tengfei Luo","orcid":"https://orcid.org/0000-0002-0126-1443"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tengfei Luo","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029114040","display_name":"Olaf Wiest","orcid":"https://orcid.org/0000-0001-9316-7720"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olaf Wiest","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000755750","display_name":"Xiangliang Zhang","orcid":"https://orcid.org/0000-0002-3574-5665"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangliang Zhang","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068157871","display_name":"Nitesh V. Chawla","orcid":"https://orcid.org/0000-0003-3932-5956"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nitesh V. Chawla","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101833672"],"corresponding_institution_ids":["https://openalex.org/I107639228"],"apc_list":null,"apc_paid":null,"fwci":0.7024,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76496722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3797","last_page":"3801"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6181870102882385},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5646026134490967},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.4067450761795044},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3201749920845032},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.1542513072490692}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6181870102882385},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5646026134490967},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.4067450761795044},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3201749920845032},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.1542513072490692}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679874","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679874","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3627673.3679874?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3627673.3679874","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679874","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3627673.3679874?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G1696205824","display_name":null,"funder_award_id":"CHE-2202693","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G356514451","display_name":null,"funder_award_id":"2202693","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5350220339","display_name":null,"funder_award_id":"2202693","funder_id":"https://openalex.org/F4320337393","funder_display_name":"Division of Chemistry"},{"id":"https://openalex.org/G5921281487","display_name":null,"funder_award_id":"number","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6073209943","display_name":null,"funder_award_id":"CHE-2202693","funder_id":"https://openalex.org/F4320337393","funder_display_name":"Division of Chemistry"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337393","display_name":"Division of Chemistry","ror":"https://ror.org/01ar8dr59"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403577809.pdf","grobid_xml":"https://content.openalex.org/works/W4403577809.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2937307539","https://openalex.org/W2963532001","https://openalex.org/W3130274530","https://openalex.org/W3165369424","https://openalex.org/W3209726219","https://openalex.org/W4324122028","https://openalex.org/W4378942305","https://openalex.org/W4386902993"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W2948807893","https://openalex.org/W2899084033","https://openalex.org/W2778153218","https://openalex.org/W2748952813","https://openalex.org/W1531601525","https://openalex.org/W4391375266","https://openalex.org/W2078814861","https://openalex.org/W2527526854","https://openalex.org/W1976181487"],"abstract_inverted_index":{"Chemical":[0],"reaction":[1,25,83,171],"data":[2,84,125,172],"has":[3],"existed":[4],"and":[5,24,33,58,87,99,116,140,153],"still":[6],"largely":[7],"exists":[8],"in":[9,54,64,182],"unstructured":[10,73],"forms.":[11],"But":[12],"curating":[13],"such":[14,21],"information":[15,57],"into":[16],"datasets":[17],"suitable":[18],"for":[19,169],"tasks":[20],"as":[22,48],"yield":[23],"outcome":[26],"prediction":[27],"is":[28],"impractical":[29],"via":[30],"manual":[31],"curation":[32],"not":[34],"possible":[35],"to":[36,85,102,158],"automate":[37],"through":[38],"programmatic":[39],"means":[40],"alone.":[41],"Large":[42],"language":[43],"models":[44,118,145],"(LLMs)":[45],"have":[46],"emerged":[47],"potent":[49],"tools,":[50],"showcasing":[51],"remarkable":[52],"capabilities":[53,110],"processing":[55],"textual":[56],"therefore":[59],"could":[60],"be":[61],"extremely":[62],"useful":[63],"automating":[65],"this":[66],"process.":[67],"To":[68],"address":[69],"the":[70,104,109,124,137,177],"challenge":[71],"of":[72,80,111,134,148],"data,":[74],"we":[75],"manually":[76],"curated":[77],"a":[78,92,100],"dataset":[79],"structured":[81],"chemical":[82,170,183],"fine-tune":[86],"evaluate":[88,108],"LLMs.":[89],"We":[90,107,185],"propose":[91],"paradigm":[93],"that":[94,131],"leverages":[95],"prompt-tuning,":[96],"fine-tuning":[97],"techniques,":[98],"verifier":[101],"check":[103],"extracted":[105],"information.":[106,184],"various":[112],"LLMs,":[113],"including":[114],"LLAMA-2":[115,144],"GPT":[117],"with":[119,146,180],"different":[120],"parameter":[121],"counts,":[122],"on":[123],"extraction":[126,173],"task.":[127],"Our":[128],"results":[129],"show":[130],"prompt":[132],"tuning":[133],"GPT-4":[135],"yields":[136],"best":[138],"accuracy":[139],"evaluation":[141],"results.":[142],"Fine-tuning":[143],"hundreds":[147],"samples":[149],"does":[150],"enable":[151],"them":[152],"organize":[154],"scientific":[155],"material":[156],"according":[157],"user-defined":[159],"schemas":[160],"better":[161],"though.":[162],"This":[163],"workflow":[164],"shows":[165],"an":[166],"adaptable":[167],"approach":[168],"but":[174],"also":[175],"highlights":[176],"challenges":[178],"associated":[179],"nuance":[181],"open-sourced":[186],"our":[187],"code":[188],"at":[189],"https://github.com/joker-bruce/LLM_Extraction_Chem.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}