{"id":"https://openalex.org/W4396597709","doi":"https://doi.org/10.1109/tkde.2024.3393356","title":"Empowering Molecule Discovery for Molecule-Caption Translation With Large Language Models: A ChatGPT Perspective","display_name":"Empowering Molecule Discovery for Molecule-Caption Translation With Large Language Models: A ChatGPT Perspective","publication_year":2024,"publication_date":"2024-05-02","ids":{"openalex":"https://openalex.org/W4396597709","doi":"https://doi.org/10.1109/tkde.2024.3393356"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2024.3393356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2024.3393356","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-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/A5101642273","display_name":"Jiatong Li","orcid":"https://orcid.org/0000-0001-7705-2296"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Jiatong Li","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","Department of Computing (COMP), The Hong Kong Polytechnic University"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Computing (COMP), The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114910997","display_name":"Yunqing Liu","orcid":"https://orcid.org/0000-0002-7049-2763"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yunqing Liu","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","Department of Computing (COMP), The Hong Kong Polytechnic University"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Computing (COMP), The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043696243","display_name":"Wenqi Fan","orcid":"https://orcid.org/0000-0002-4049-1233"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wenqi Fan","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","Department of Computing (COMP), The Hong Kong Polytechnic University"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Computing (COMP), The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034340826","display_name":"Xiaoyong Wei","orcid":"https://orcid.org/0000-0001-9677-4227"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiao-Yong Wei","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","Department of Computing (COMP), The Hong Kong Polytechnic University"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Computing (COMP), The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101566727","display_name":"Hui Liu","orcid":"https://orcid.org/0009-0007-9389-7038"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]},{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["HK","US"],"is_corresponding":false,"raw_author_name":"Hui Liu","raw_affiliation_strings":["Michigan State University, East Lansing, MI, USA","Department of Computing, The Hong Kong Polytechnic University"],"affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]},{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040639891","display_name":"Jiliang Tang","orcid":"https://orcid.org/0000-0001-7125-3898"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]},{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["HK","US"],"is_corresponding":false,"raw_author_name":"Jiliang Tang","raw_affiliation_strings":["Michigan State University, East Lansing, MI, USA","Department of Computing, The Hong Kong Polytechnic University"],"affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]},{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100404176","display_name":"Qing Li","orcid":"https://orcid.org/0000-0003-3370-471X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qing Li","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","Department of Computing (COMP), The Hong Kong Polytechnic University"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Computing (COMP), The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101642273"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":17.8861,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.99414994,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"36","issue":"11","first_page":"6071","last_page":"6083"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9735999703407288,"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":0.9735999703407288,"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":0.9506999850273132,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9448000192642212,"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/computer-science","display_name":"Computer science","score":0.7688403129577637},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6348608136177063},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5736487507820129},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4255434572696686},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34412848949432373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2875821590423584},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.10026884078979492}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688403129577637},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6348608136177063},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5736487507820129},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4255434572696686},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34412848949432373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2875821590423584},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.10026884078979492},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2024.3393356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2024.3393356","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4078110728","display_name":null,"funder_award_id":"P0048625","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"},{"id":"https://openalex.org/G450452401","display_name":null,"funder_award_id":"P0036200","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"},{"id":"https://openalex.org/G490123725","display_name":null,"funder_award_id":"62102335","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G528947399","display_name":null,"funder_award_id":"P0042693","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"},{"id":"https://openalex.org/G8216508967","display_name":null,"funder_award_id":"P0048752","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W1984994707","https://openalex.org/W2101746535","https://openalex.org/W2338373933","https://openalex.org/W2931503046","https://openalex.org/W2982893348","https://openalex.org/W2984587394","https://openalex.org/W2986232138","https://openalex.org/W2989615256","https://openalex.org/W2999242200","https://openalex.org/W3043096321","https://openalex.org/W3093934881","https://openalex.org/W3136005985","https://openalex.org/W3207373390","https://openalex.org/W3209056694","https://openalex.org/W3210277894","https://openalex.org/W3211951295","https://openalex.org/W4207035044","https://openalex.org/W4212837331","https://openalex.org/W4220699355","https://openalex.org/W4224308101","https://openalex.org/W4226399820","https://openalex.org/W4252076394","https://openalex.org/W4287891464","https://openalex.org/W4288089799","https://openalex.org/W4289595467","https://openalex.org/W4295846611","https://openalex.org/W4316036243","https://openalex.org/W4322718191","https://openalex.org/W4323065907","https://openalex.org/W4366850747","https://openalex.org/W4377096651","https://openalex.org/W4385764461","https://openalex.org/W4386728933","https://openalex.org/W4387874094","https://openalex.org/W4389888290","https://openalex.org/W4396723768","https://openalex.org/W6739901393","https://openalex.org/W6769627184","https://openalex.org/W6770131888","https://openalex.org/W6784526300","https://openalex.org/W6810047384","https://openalex.org/W6810081322","https://openalex.org/W6810738896","https://openalex.org/W6811129797","https://openalex.org/W6842368577","https://openalex.org/W6849862423","https://openalex.org/W6850625674","https://openalex.org/W6851950068"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2775554247","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2110168585","https://openalex.org/W3107474891","https://openalex.org/W2250213760","https://openalex.org/W4386247111","https://openalex.org/W4327642362","https://openalex.org/W2587014613"],"abstract_inverted_index":{"Molecule":[0,148],"discovery":[1,156,278],"plays":[2],"a":[3,134,188,273],"crucial":[4],"role":[5],"in":[6,78,87,112,122,254],"various":[7,79],"scientific":[8],"fields,":[9],"advancing":[10,258],"the":[11,21,47,65,115,174,196,204,238,245,264],"design":[12],"of":[13,23,46,117,176,206,240,266],"tailored":[14],"materials":[15],"and":[16,25,92,120,170,183,214,229,279],"drugs,":[17],"which":[18,96],"contributes":[19],"to":[20,83,100,109,153,161,179,191,194,223,232,248],"development":[22],"society":[24],"human":[26,39],"well-being.":[27],"Specifically,":[28],"molecule-caption":[29,142,209,255],"translation":[30,256],"is":[31,151,230,244],"an":[32,145],"important":[33],"task":[34,197],"for":[35,141,257,276],"molecule":[36,102,155,212,216,259,277],"discovery,":[37],"aligning":[38],"understanding":[40,213],"with":[41,157],"molecular":[42,177],"space.":[43],"However,":[44],"most":[45],"existing":[48],"methods":[49],"heavily":[50],"rely":[51],"on":[52,208],"domain":[53],"experts,":[54],"require":[55],"excessive":[56],"computational":[57],"cost,":[58],"or":[59],"suffer":[60],"from":[61,187,199],"sub-optimal":[62],"performance.":[63],"On":[64],"other":[66],"hand,":[67],"Large":[68],"Language":[69],"Models":[70],"(LLMs),":[71],"like":[72,159],"ChatGPT,":[73],"have":[74],"shown":[75],"remarkable":[76],"performance":[77],"cross-modal":[80],"tasks":[81],"due":[82],"their":[84,163,184],"powerful":[85],"capabilities":[86],"natural":[88],"language":[89],"understanding,":[90],"generalization,":[91],"in-context":[93,164,252],"learning":[94,165,253],"(ICL),":[95],"provides":[97],"unprecedented":[98],"opportunities":[99],"advance":[101],"discovery.":[103,260],"Despite":[104],"several":[105],"previous":[106],"works":[107],"trying":[108],"apply":[110],"LLMs":[111,125,158,193,250],"this":[113,130],"task,":[114],"lack":[116],"domain-specific":[118,168],"corpus":[119],"difficulties":[121],"training":[123],"specialized":[124],"still":[126],"remain":[127],"challenges.":[128],"In":[129],"work,":[131],"we":[132],"propose":[133],"novel":[135],"LLM-based":[136],"framework":[137],"(<bold":[138],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[139],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">MolReGPT</b>)":[140],"translation,":[143,210],"where":[144],"In-Context":[146],"Few-Shot":[147],"Learning":[149],"paradigm":[150,275],"introduced":[152],"empower":[154],"ChatGPT":[160],"perform":[162],"capability":[166],"without":[167,234],"pre-training":[169],"fine-tuning.":[171],"MolReGPT":[172,207,226,243],"leverages":[173],"principle":[175],"similarity":[178],"retrieve":[180],"similar":[181],"molecules":[182],"text":[185],"descriptions":[186],"local":[189],"database":[190],"enable":[192],"learn":[195],"knowledge":[198],"context":[200],"examples.":[201],"We":[202],"evaluate":[203],"effectiveness":[205],"including":[211],"text-based":[215],"generation.":[217],"Experimental":[218],"results":[219],"show":[220],"that":[221],"compared":[222],"fine-tuned":[224],"models,":[225],"outperforms":[227],"MolT5-base":[228],"comparable":[231],"MolT5-large":[233],"additional":[235],"training.":[236],"To":[237],"best":[239],"our":[241],"knowledge,":[242],"first":[246],"work":[247,262],"leverage":[249],"via":[251],"Our":[261],"expands":[263],"scope":[265],"LLM":[267],"applications,":[268],"as":[269,271],"well":[270],"providing":[272],"new":[274],"design.":[280]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":13}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}