{"id":"https://openalex.org/W4409134050","doi":"https://doi.org/10.1109/tkde.2025.3557697","title":"Large Language Models are In-Context Molecule Learners","display_name":"Large Language Models are In-Context Molecule Learners","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409134050","doi":"https://doi.org/10.1109/tkde.2025.3557697"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2025.3557697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2025.3557697","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/A5101642271","display_name":"Jiatong Li","orcid":"https://orcid.org/0000-0003-0084-2470"},"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, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100763571","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-0797-4612"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101597644","display_name":"Zhihao Ding","orcid":"https://orcid.org/0009-0003-2303-5599"},"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":"Zhihao Ding","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong","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, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055664612","display_name":"Yuqiang Li","orcid":"https://orcid.org/0000-0001-6756-6154"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqiang Li","raw_affiliation_strings":["Shanghai AI Lab, China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Lab, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100404020","display_name":"Qing Li","orcid":"https://orcid.org/0000-0001-7170-4679"},"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, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101642271"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":5.6903,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95036556,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9653000235557556,"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":0.9653000235557556,"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":0.9603999853134155,"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":0.8206520080566406},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5192732810974121},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.45527997612953186},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4212999939918518},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.324762225151062},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31163322925567627}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8206520080566406},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5192732810974121},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.45527997612953186},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4212999939918518},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.324762225151062},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31163322925567627},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2025.3557697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2025.3557697","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":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W2167381455","https://openalex.org/W2594183968","https://openalex.org/W2899070097","https://openalex.org/W2970641574","https://openalex.org/W2982893348","https://openalex.org/W3009321976","https://openalex.org/W3211951295","https://openalex.org/W4226048133","https://openalex.org/W4252076394","https://openalex.org/W4289595467","https://openalex.org/W4365455552","https://openalex.org/W4385572408","https://openalex.org/W4385572634","https://openalex.org/W4385767952","https://openalex.org/W4389523890","https://openalex.org/W4389524207","https://openalex.org/W4391561379","https://openalex.org/W4396597709","https://openalex.org/W4404782964","https://openalex.org/W6778883912","https://openalex.org/W6796581206","https://openalex.org/W6809646742","https://openalex.org/W6810047384","https://openalex.org/W6810081322","https://openalex.org/W6842368577","https://openalex.org/W6849177959","https://openalex.org/W6849941170","https://openalex.org/W6854029451","https://openalex.org/W6854122679","https://openalex.org/W6858023062"],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W2349222429","https://openalex.org/W2116230991","https://openalex.org/W3117430770","https://openalex.org/W2046058552","https://openalex.org/W2590751808","https://openalex.org/W1972377868","https://openalex.org/W2132709506","https://openalex.org/W2098730537","https://openalex.org/W2186895195"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"exceptional":[6],"performance":[7,187],"in":[8,32],"biochemical":[9],"tasks,":[10],"especially":[11],"the":[12,21,36,58,64,80,93,139,149,158,163],"molecule":[13,201],"caption":[14],"translation":[15,38],"task,":[16],"which":[17],"aims":[18],"to":[19,35,78,118,136,182],"bridge":[20],"gap":[22],"between":[23,48,170],"molecules":[24,171],"and":[25,50,102,114,132,152,161,172,192],"natural":[26],"language":[27],"texts.":[28,173],"However,":[29],"previous":[30],"methods":[31],"adapting":[33],"LLMs":[34,77,156,166,181,197],"molecule-caption":[37],"task":[39],"required":[40],"extra":[41,189],"domain-specific":[42],"pre-training":[43],"stages,":[44],"suffered":[45],"weak":[46],"alignment":[47,82,169],"molecular":[49],"textual":[51],"spaces,":[52],"or":[53,185],"imposed":[54],"stringent":[55],"demands":[56],"on":[57],"scale":[59],"of":[60,129,141,155,165],"LLMs.":[61],"To":[62],"resolve":[63],"challenges,":[65],"we":[66],"propose":[67],"In-Context":[68,87,145],"Molecule":[69,88,104,115,146],"Adaptation":[70],"(ICMA),":[71],"as":[72],"a":[73],"new":[74],"paradigm":[75],"allowing":[76],"learn":[79],"molecule-text":[81],"from":[83],"context":[84,122],"examples":[85,160],"via":[86],"Tuning.":[89,105],"Specifically,":[90],"ICMA":[91,178],"incorporates":[92],"following":[94],"three":[95],"stages:":[96],"Hybrid":[97,107],"Context":[98,108],"Retrieval,":[99],"Post-retrieval":[100,125],"Re-ranking,":[101],"In-context":[103],"Initially,":[106],"Retrieval":[109,113,117],"utilizes":[110],"BM25":[111],"Caption":[112],"Graph":[116],"retrieve":[119],"similar":[120],"informative":[121],"examples.":[123],"Additionally,":[124],"Re-ranking":[126],"is":[127],"composed":[128],"Sequence":[130],"Reversal":[131],"Random":[133],"Walk":[134],"selection":[135],"further":[137],"improve":[138],"quality":[140],"retrieval":[142],"results.":[143],"Finally,":[144],"Tuning":[147],"unlocks":[148],"in-context":[150,200],"learning":[151],"reasoning":[153],"capability":[154],"with":[157],"retrieved":[159],"adapts":[162],"parameters":[164],"for":[167],"better":[168],"Experimental":[174],"results":[175],"demonstrate":[176],"that":[177,196],"can":[179],"empower":[180],"achieve":[183],"state-of-the-art":[184],"comparable":[186],"without":[188],"training":[190],"corpora":[191],"intricate":[193],"structures,":[194],"showing":[195],"are":[198],"inherently":[199],"learners.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-04T07:04:00.330322","created_date":"2025-10-10T00:00:00"}