{"id":"https://openalex.org/W4412945209","doi":"https://doi.org/10.18653/v1/2025.acl-long.755","title":"MolRAG: Unlocking the Power of Large Language Models for Molecular Property Prediction","display_name":"MolRAG: Unlocking the Power of Large Language Models for Molecular Property Prediction","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945209","doi":"https://doi.org/10.18653/v1/2025.acl-long.755"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.755","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.755","pdf_url":"https://aclanthology.org/2025.acl-long.755.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.755.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066792986","display_name":"Ziting Xian","orcid":"https://orcid.org/0009-0006-4116-6623"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]},{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I4210097354","display_name":"Sun Yat-sen Memorial Hospital","ror":"https://ror.org/01px77p81","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210097354"]}],"countries":["CN","TW"],"is_corresponding":false,"raw_author_name":"Ziting Xian","raw_affiliation_strings":["Sun Yat-sen University Sun Yat-sen University University of Warwick Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University Sun Yat-sen University University of Warwick Sun Yat-sen University","institution_ids":["https://openalex.org/I142974352","https://openalex.org/I157773358","https://openalex.org/I4210097354"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072908486","display_name":"Jing Gu","orcid":"https://orcid.org/0000-0002-0291-3263"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]},{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I4210097354","display_name":"Sun Yat-sen Memorial Hospital","ror":"https://ror.org/01px77p81","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210097354"]}],"countries":["CN","TW"],"is_corresponding":false,"raw_author_name":"Jiawei Gu","raw_affiliation_strings":["Sun Yat-sen University Sun Yat-sen University University of Warwick Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University Sun Yat-sen University University of Warwick Sun Yat-sen University","institution_ids":["https://openalex.org/I142974352","https://openalex.org/I157773358","https://openalex.org/I4210097354"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119204475","display_name":"Lingbo Li","orcid":null},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]},{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I4210097354","display_name":"Sun Yat-sen Memorial Hospital","ror":"https://ror.org/01px77p81","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210097354"]}],"countries":["CN","TW"],"is_corresponding":false,"raw_author_name":"Lingbo Li","raw_affiliation_strings":["Sun Yat-sen University Sun Yat-sen University University of Warwick Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University Sun Yat-sen University University of Warwick Sun Yat-sen University","institution_ids":["https://openalex.org/I142974352","https://openalex.org/I157773358","https://openalex.org/I4210097354"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060335069","display_name":"Shangsong Liang","orcid":"https://orcid.org/0000-0003-1625-2168"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]},{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I4210097354","display_name":"Sun Yat-sen Memorial Hospital","ror":"https://ror.org/01px77p81","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210097354"]}],"countries":["CN","TW"],"is_corresponding":false,"raw_author_name":"Shangsong Liang","raw_affiliation_strings":["Sun Yat-sen University Sun Yat-sen University University of Warwick Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University Sun Yat-sen University University of Warwick Sun Yat-sen University","institution_ids":["https://openalex.org/I142974352","https://openalex.org/I157773358","https://openalex.org/I4210097354"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.6269,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.99216087,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"15513","last_page":"15531"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9969000220298767,"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"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9969000220298767,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9969000220298767,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.6885722875595093},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6042463779449463}],"concepts":[{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.6885722875595093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6042463779449463},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.755","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.755","pdf_url":"https://aclanthology.org/2025.acl-long.755.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.755","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.755","pdf_url":"https://aclanthology.org/2025.acl-long.755.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945209.pdf","grobid_xml":"https://content.openalex.org/works/W4412945209.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Recent":[0],"LLMs":[1,86],"exhibit":[2],"limited":[3],"effectiveness":[4],"on":[5,87],"molecular":[6,16,43,67],"property":[7,44],"prediction":[8,101],"task":[9],"due":[10],"to":[11,55,199,220],"the":[12,24,160,191,195,200,223,321],"semantic":[13],"gap":[14],"between":[15],"representations":[17],"and":[18,90,213,264,285,305,331,356],"natural":[19],"language,":[20],"as":[21,23,52],"well":[22],"lack":[25],"of":[26,98],"domain-specific":[27],"knowledge.To":[28],"address":[29],"these":[30],"challenges,":[31],"we":[32],"propose":[33],"MolRAG,":[34],"a":[35,182,207,214,228,256,260,265,277,281,297,301,306,327,332,347,352,357],"Retrieval-Augmented":[36],"Generation":[37],"framework":[38],"integrating":[39],"Chain-of-Thought":[40],"reasoning":[41,59],"for":[42],"prediction.MolRAG":[45],"operates":[46],"by":[47],"retrieving":[48],"structurally":[49],"analogous":[50],"molecules":[51],"contextual":[53],"references":[54],"guide":[56],"stepwise":[57],"knowledge":[58],"through":[60],"chemical":[61],"structureproperty":[62],"relationships.This":[63],"dual":[64],"mechanism":[65],"synergizes":[66],"similarity":[68],"analysis":[69],"with":[70,190,259,280,300,351],"structured":[71],"inference,":[72],"while":[73],"generating":[74],"humaninterpretable":[75],"rationales":[76],"grounded":[77],"in":[78,235],"domain":[79],"knowledge.Experimental":[80],"results":[81],"show":[82],"Mol-RAG":[83],"outperforms":[84],"pre-trained":[85],"four":[88],"datasets,":[89],"even":[91],"matches":[92],"supervised":[93],"methods,":[94],"achieving":[95],"performance":[96],"gains":[97],"1.1%-45.7%over":[99],"direct":[100],"approaches,":[102],"demonstrating":[103],"versatile":[104],"effectiveness.Our":[105],"code":[106],"is":[107,232],"available":[108],"at":[109],"https://github.com/AcaciaSin/MolRAG.*":[110],"Molecule":[111,123,134,147,221,236],"1:":[112],"No":[113,149,251,272,292,317],"3D":[114,131,140,155,179,215],"structure,":[115,141,216,258,279,299],"no":[116,119,130,143,154,286,311,338],"sulfone":[117,150,169,187,208],"group,":[118,126,137,151,209],"aromatic":[120,127,138,152,174,211,354],"ring":[121,145,175,193,355],"*":[122,133,146,167,172,177,185,238,254,275,295,324,344],"2:":[124,253],"Sulfone":[125,136],"ring,":[128,139,153,212,230],"but":[129,142,310],"structure":[132,156,180,350],"3:":[135,274],"nitrogen-containing":[144,183,192,229],"4:":[148,294],"Now,":[157,318],"let's":[158,319],"analyze":[159,320],"question":[161,196,224],"input":[162,197,225,322],"molecule:":[163,323],"O=SThis":[164],"molecule":[165,198,226],"has:":[166],"A":[168,178,186],"group":[170,188,262,267,283,303,329,334],"(S(=O)(=O)O)":[171],"An":[173],"(c1cc2...)":[176],"(with":[181],"ring)":[184],"interacting":[189],"Comparing":[194],"examples,":[201],"I":[202],"notice":[203],"that":[204],"it":[205],"has":[206,227,326,337,346],"an":[210],"which":[217,231,243],"are":[218],"similar":[219],"3.However,":[222],"not":[233],"present":[234],"3.":[237],"Has":[239,255,276,296],"fluorine":[240,339],"atoms":[241],"(C(F)(F)F)":[242],"may":[244],"affect":[245],"its":[246],"properties.*":[247],"Score:":[248,269,289,314],"0.6575,":[249],"Label:":[250,271,291,316],"Example":[252,273,293,342],"different":[257,278,298],"carbonyl":[261,282,333],"(C(=O)CC(c2ccccc2))":[263],"sulfonamide":[266,287,312,328,358],"(Sc2ccccc21).*":[268],"0.5634,":[270],"(C(=O)c2cc3ccccc3cc21)":[284],"group.*":[288,313],"0.5397,":[290],"hydroxyl":[302],"(O)":[304],"bromine":[307],"atom":[308],"(Br),":[309],"0.5312,":[315],"It":[325,336,345],"(Sc2c1ccc1ccccc21)":[330],"(CC(=O)N1c2ccccc2).*":[335],"atoms,":[340],"unlike":[341],"1.":[343],"relatively":[348],"simple":[349],"single":[353],"group.":[359]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}