{"id":"https://openalex.org/W4416033970","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.996","title":"GAMIC: Graph-Aligned Molecular In-context Learning for Molecule Analysis via LLMs","display_name":"GAMIC: Graph-Aligned Molecular In-context Learning for Molecule Analysis via LLMs","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416033970","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.996"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.996","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.996","pdf_url":"https://aclanthology.org/2025.findings-emnlp.996.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.996.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120308453","display_name":"Ali Al Lawati","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali Al Lawati","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060378653","display_name":"Jason Samuel Lucas","orcid":"https://orcid.org/0009-0000-3494-6935"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jason S Lucas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100347599","display_name":"Zhiwei Zhang","orcid":"https://orcid.org/0000-0002-3187-9180"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiwei Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009542542","display_name":"Prasenjit Mitra","orcid":"https://orcid.org/0000-0002-7530-9497"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prasenjit Mitra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5011048500","display_name":"Suhang Wang","orcid":"https://orcid.org/0000-0003-3448-4878"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suhang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29689845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18364","last_page":"18378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.41990000009536743,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.41990000009536743,"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":0.14069999754428864,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.13490000367164612,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/molecule","display_name":"Molecule","score":0.2669999897480011},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2558000087738037},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.2485000044107437},{"id":"https://openalex.org/keywords/mutation","display_name":"Mutation","score":0.24300000071525574},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.24220000207424164}],"concepts":[{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.4823000133037567},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.32829999923706055},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2808000147342682},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2485000044107437},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.2443999946117401},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.24300000071525574},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.24220000207424164},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.23749999701976776}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.996","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.996","pdf_url":"https://aclanthology.org/2025.findings-emnlp.996.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.996","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.996","pdf_url":"https://aclanthology.org/2025.findings-emnlp.996.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416033970.pdf","grobid_xml":"https://content.openalex.org/works/W4416033970.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In-context":[0],"learning":[1,107],"(ICL)":[2],"effectively":[3],"conditions":[4],"large":[5],"language":[6],"models":[7],"(LLMs)":[8],"for":[9,43],"molecular":[10,44,62,77,97,117],"tasks,":[11],"such":[12,51],"as":[13,52],"property":[14],"prediction":[15],"and":[16,37,63],"molecule":[17,48],"captioning,":[18],"by":[19,120,173],"embedding":[20],"carefully":[21],"selected":[22],"demonstration":[23,154],"examples":[24],"into":[25],"the":[26,31,60,73,96],"input":[27,152],"prompt.This":[28],"approach":[29],"eliminates":[30],"computational":[32],"overhead":[33],"of":[34,76],"extensive":[35],"pre-training":[36],"fine-tuning.However,":[38],"current":[39],"prompt":[40,153],"retrieval":[41,149,168],"methods":[42,69,169],"tasks":[45,172],"rely":[46],"on":[47],"feature":[49,132],"similarity,":[50],"Morgan":[53,135],"fingerprints,":[54],"which":[55,83,114],"do":[56],"not":[57],"adequately":[58],"capture":[59],"global":[61,116],"atom-binding":[64],"relationships.As":[65],"a":[66,105,140],"result,":[67],"these":[68,101],"fail":[70],"to":[71,150,175],"represent":[72],"full":[74],"complexity":[75],"structures":[78],"during":[79,148],"inference.Moreover,":[80],"medium-sized":[81],"LLMs,":[82],"offer":[84],"simpler":[85],"deployment":[86],"requirements":[87],"in":[88,95],"specialized":[89],"systems,":[90],"have":[91],"remained":[92],"largely":[93],"unexplored":[94],"ICL":[98,167],"literature.To":[99],"address":[100],"gaps,":[102],"we":[103,138],"propose":[104],"self-supervised":[106],"technique,":[108],"GAMIC":[109,163],"(Graph-Aligned":[110],"Molecular":[111],"In-Context":[112],"learning),":[113],"aligns":[115],"structures,":[118],"represented":[119],"graph":[121],"neural":[122],"networks":[123],"(GNNs),":[124],"with":[125],"textual":[126],"captions":[127],"(descriptions)":[128],"while":[129],"leveraging":[130],"local":[131],"similarity":[133],"through":[134],"fingerprints.In":[136],"addition,":[137],"introduce":[139],"Maximum":[141],"Marginal":[142],"Relevance":[143],"(MMR)":[144],"based":[145],"diversity":[146],"heuristic":[147],"optimize":[151],"samples.Our":[155],"experimental":[156],"findings":[157],"using":[158],"diverse":[159],"benchmark":[160],"datasets":[161],"show":[162],"outperforms":[164],"simple":[165],"Morgan-based":[166],"across":[170],"all":[171],"up":[174],"45%.":[176],"1":[177]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}