{"id":"https://openalex.org/W4414359667","doi":"https://doi.org/10.24963/ijcai.2025/840","title":"Enhancing Chemical Reaction and Retrosynthesis Prediction with Large Language Model and Dual-task Learning","display_name":"Enhancing Chemical Reaction and Retrosynthesis Prediction with Large Language Model and Dual-task Learning","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359667","doi":"https://doi.org/10.24963/ijcai.2025/840"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/840","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","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/A5027410770","display_name":"Xuan Lin","orcid":"https://orcid.org/0000-0001-7216-1821"},"institutions":[{"id":"https://openalex.org/I4610292","display_name":"Xiangtan University","ror":"https://ror.org/00xsfaz62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4610292"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Lin","raw_affiliation_strings":["Xiangtan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiangtan University","institution_ids":["https://openalex.org/I4610292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088265452","display_name":"Qingrui Liu","orcid":"https://orcid.org/0000-0001-9481-431X"},"institutions":[{"id":"https://openalex.org/I4610292","display_name":"Xiangtan University","ror":"https://ror.org/00xsfaz62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4610292"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingrui Liu","raw_affiliation_strings":["Xiangtan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiangtan University","institution_ids":["https://openalex.org/I4610292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000226430","display_name":"Hongxin Xiang","orcid":"https://orcid.org/0000-0001-8345-8735"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongxin Xiang","raw_affiliation_strings":["Hunan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039880027","display_name":"Daojian Zeng","orcid":"https://orcid.org/0000-0002-3552-0685"},"institutions":[{"id":"https://openalex.org/I173759888","display_name":"Hunan Normal University","ror":"https://ror.org/053w1zy07","country_code":"CN","type":"education","lineage":["https://openalex.org/I173759888"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daojian Zeng","raw_affiliation_strings":["Hunan Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan Normal University","institution_ids":["https://openalex.org/I173759888"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027286013","display_name":"Xiangxiang Zeng","orcid":"https://orcid.org/0000-0003-1081-7658"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangxiang Zeng","raw_affiliation_strings":["Hunan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7554","last_page":"7562"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14249","display_name":"Water Quality Monitoring and Analysis","score":0.7296000123023987,"subfield":{"id":"https://openalex.org/subfields/2311","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14249","display_name":"Water Quality Monitoring and Analysis","score":0.7296000123023987,"subfield":{"id":"https://openalex.org/subfields/2311","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.6320000290870667,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.609499990940094,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/retrosynthetic-analysis","display_name":"Retrosynthetic analysis","score":0.9556000232696533},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5825999975204468},{"id":"https://openalex.org/keywords/fragmentation","display_name":"Fragmentation (computing)","score":0.5475999712944031},{"id":"https://openalex.org/keywords/drug-target","display_name":"Drug target","score":0.384799987077713},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3402999937534332},{"id":"https://openalex.org/keywords/drug-reaction","display_name":"Drug reaction","score":0.2840999960899353}],"concepts":[{"id":"https://openalex.org/C42437451","wikidata":"https://www.wikidata.org/wiki/Q902227","display_name":"Retrosynthetic analysis","level":3,"score":0.9556000232696533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6599000096321106},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5825999975204468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5677000284194946},{"id":"https://openalex.org/C191015642","wikidata":"https://www.wikidata.org/wiki/Q1132459","display_name":"Fragmentation (computing)","level":2,"score":0.5475999712944031},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3991999924182892},{"id":"https://openalex.org/C2989108626","wikidata":"https://www.wikidata.org/wiki/Q904407","display_name":"Drug target","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33980000019073486},{"id":"https://openalex.org/C2993432071","wikidata":"https://www.wikidata.org/wiki/Q45959","display_name":"Drug reaction","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.259799987077713}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/840","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Chemical":[0],"reaction":[1,47,80,133,154],"and":[2,48,81,94,114,125,134,141,155,163,177],"retrosynthesis":[3,49,135],"prediction":[4,50],"are":[5],"fundamental":[6],"tasks":[7,28,131],"in":[8,19,150,187],"drug":[9,188],"discovery.":[10],"Recently,":[11],"large":[12],"language":[13],"models":[14],"(LLMs)":[15],"have":[16],"shown":[17],"potential":[18,186],"many":[20],"domains.":[21],"However,":[22],"directly":[23],"applying":[24],"LLMs":[25],"to":[26,118],"these":[27,58],"faces":[29],"two":[30],"major":[31],"challenges:":[32],"(i)":[33],"lacking":[34],"a":[35,63,90,96,111],"large-scale":[36,97],"chemical":[37,69],"synthesis-related":[38],"instruction":[39,101],"dataset;":[40],"(ii)":[41],"ignoring":[42],"the":[43,52,73,85,121,130,158,164],"close":[44],"correlation":[45],"between":[46,132],"for":[51,67,79],"existing":[53,159],"fine-tuning":[54],"strategies.":[55],"To":[56],"address":[57],"challenges,":[59],"we":[60],"propose":[61],"ChemDual,":[62],"novel":[64],"LLM":[65],"framework":[66],"accurate":[68],"synthesis.":[70],"Specifically,":[71],"considering":[72],"high":[74],"cost":[75],"of":[76,87,98,123,153],"data":[77],"acquisition":[78],"retrosynthesis,":[82,156],"ChemDual":[83,104,146,172],"regards":[84],"reaction-and-retrosynthesis":[86],"molecules":[88],"as":[89,127,129],"related":[91],"recombination-and-fragmentation":[92],"process":[93,122],"constructs":[95],"4.4":[99],"million":[100],"dataset.":[102],"Furthermore,":[103],"introduces":[105],"an":[106],"enhanced":[107],"LLaMA,":[108],"equipped":[109],"with":[110,175],"multi-scale":[112],"tokenizer":[113],"dual-task":[115],"learning":[116],"strategy,":[117],"jointly":[119],"optimize":[120],"recombination":[124],"fragmentation":[126],"well":[128],"prediction.":[136],"Extensive":[137],"experiments":[138],"on":[139],"Mol-Instruction":[140],"USPTO-50K":[142],"datasets":[143],"demonstrate":[144],"that":[145],"achieves":[147],"state-of-the-art":[148],"performance":[149],"both":[151],"predictions":[152],"outperforming":[157],"conventional":[160],"single-task":[161],"approaches":[162],"general":[165],"open-source":[166],"LLMs.":[167],"Through":[168],"molecular":[169],"docking":[170],"analysis,":[171],"generates":[173],"compounds":[174],"diverse":[176],"strong":[178,185],"protein":[179],"binding":[180],"affinity,":[181],"further":[182],"highlighting":[183],"its":[184],"design.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}