{"id":"https://openalex.org/W7204280403","doi":"https://doi.org/10.26434/chemrxiv.15007879/v1","title":"Large Language Models for Molecular Science: A Survey on Representation and Cognition","display_name":"Large Language Models for Molecular Science: A Survey on Representation and Cognition","publication_year":2026,"publication_date":"2026-08-26","ids":{"openalex":"https://openalex.org/W7204280403","doi":"https://doi.org/10.26434/chemrxiv.15007879/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15007879/v1","doi":"https://doi.org/10.26434/chemrxiv.15007879/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15007879/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.26434/chemrxiv.15007879/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139795935","display_name":"Mingxu Zhang","orcid":"https://orcid.org/0009-0003-7451-7950","observed_orcids":["https://orcid.org/0009-0003-7451-7950"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxu Zhang","raw_affiliation_strings":["AI Thrust","Hong Kong University of Science and Technology (Guangzhou"],"raw_orcid":"https://orcid.org/0009-0003-7451-7950","affiliations":[{"raw_affiliation_string":"AI Thrust","institution_ids":[]},{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332402","display_name":"Yuhan Li","orcid":"https://orcid.org/0000-0003-1324-5819","observed_orcids":["https://orcid.org/0000-0003-1324-5819"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhan Li","raw_affiliation_strings":["AI Thrust","Hong Kong University of Science and Technology (Guangzhou"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Thrust","institution_ids":[]},{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046835504","display_name":"Ying Sun","orcid":"https://orcid.org/0000-0002-4763-6060","observed_orcids":["https://orcid.org/0000-0002-4763-6060"]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Sun","raw_affiliation_strings":["63rd Research Institute","National University of Defense Technology"],"raw_orcid":"https://orcid.org/0000-0002-4763-6060","affiliations":[{"raw_affiliation_string":"63rd Research Institute","institution_ids":[]},{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075007087","display_name":"Dazhong Shen","orcid":"https://orcid.org/0000-0002-3947-4153","observed_orcids":["https://orcid.org/0000-0002-3947-4153"]},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dazhong Shen","raw_affiliation_strings":["College of Computer Science and Technology","Nanjing University of Aeronautics and Astronautics"],"raw_orcid":"https://orcid.org/0000-0002-3947-4153","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology","institution_ids":[]},{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101862104","display_name":"Hui Xiong","orcid":"https://orcid.org/0000-0001-6016-6465","observed_orcids":["https://orcid.org/0000-0001-6016-6465","https://orcid.org/0000-0002-4665-9850","https://orcid.org/0000-0001-5759-3001"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Xiong","raw_affiliation_strings":["AI Thrust","Hong Kong University of Science and Technology (Guangzhou"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Thrust","institution_ids":[]},{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou","institution_ids":["https://openalex.org/I4405261251"]}]}],"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.8003000020980835,"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":0.8003000020980835,"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":0.12449999898672104,"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/T13297","display_name":"History and advancements in chemistry","score":0.016699999570846558,"subfield":{"id":"https://openalex.org/subfields/1606","display_name":"Physical and Theoretical Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9739999771118164},{"id":"https://openalex.org/keywords/molecular-representation","display_name":"molecular representation","score":0.8190000057220459},{"id":"https://openalex.org/keywords/smiles","display_name":"SMILES","score":0.7440000176429749},{"id":"https://openalex.org/keywords/selfies","display_name":"selfies","score":0.996999979019165},{"id":"https://openalex.org/keywords/equivariance","display_name":"equivariance","score":0.9350000023841858},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.7620000243186951},{"id":"https://openalex.org/keywords/tool-orchestration","display_name":"tool orchestration","score":0.7509999871253967},{"id":"https://openalex.org/keywords/chemical-reasoning","display_name":"chemical reasoning","score":0.7390000224113464},{"id":"https://openalex.org/keywords/molecular-generation","display_name":"molecular generation","score":0.44999998807907104},{"id":"https://openalex.org/keywords/autonomous-discovery","display_name":"autonomous discovery","score":0.37700000405311584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6812000274658203},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.5},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48500001430511475},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4641999900341034},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.44290000200271606},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3824000060558319},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3465000092983246},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3239000141620636},{"id":"https://openalex.org/C170494330","wikidata":"https://www.wikidata.org/wiki/Q1778434","display_name":"Cognitive map","level":3,"score":0.3190000057220459},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.3142000138759613},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.31310001015663147},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C100521375","wikidata":"https://www.wikidata.org/wiki/Q2015382","display_name":"Competence (human resources)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28139999508857727},{"id":"https://openalex.org/C66153294","wikidata":"https://www.wikidata.org/wiki/Q899291","display_name":"CASP","level":4,"score":0.27950000762939453},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15007879/v1","doi":"https://doi.org/10.26434/chemrxiv.15007879/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15007879/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15007879/v1","doi":"https://doi.org/10.26434/chemrxiv.15007879/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15007879/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391556076","https://openalex.org/W7162125939","https://openalex.org/W4415374851","https://openalex.org/W4417468204","https://openalex.org/W4398778066","https://openalex.org/W7164754431","https://openalex.org/W7213934344","https://openalex.org/W4417101782","https://openalex.org/W4404780835","https://openalex.org/W4399597633"],"abstract_inverted_index":{"The":[0],"integration":[1],"of":[2,38,48,67],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"into":[7,163],"the":[8,31,34,42,64,82,207],"natural":[9,39],"sciences":[10],"marks":[11],"a":[12,28,53,186,211],"shift":[13],"from":[14,86],"specialized":[15],"discriminative":[16],"models":[17],"to":[18,25,81,98,112,149],"generalist":[19],"generative":[20],"agents.":[21],"However,":[22],"adapting":[23],"LLMs":[24,126],"chemistry":[26],"presents":[27],"core":[29],"challenge:":[30],"mismatch":[32],"between":[33],"linear,":[35],"ambiguous":[36],"nature":[37,47],"language":[40],"and":[41,45,70,96,108,110,120,128,143,154,157,173,197,200],"discrete,":[43],"topological,":[44],"physical":[46,118,150],"molecules.":[49],"This":[50],"review":[51],"provides":[52],"systematic":[54],"framework":[55],"for":[56],"bridging":[57],"this":[58,178],"gap,":[59],"organizing":[60],"recent":[61],"advances":[62],"through":[63,106,132,141],"dual":[65],"lenses":[66],"representation":[68],"alignment":[69],"cognitive":[71],"mechanism.":[72],"First,":[73],"we":[74,123,160,181,201],"examine":[75],"how":[76,125],"molecular":[77],"modalities":[78],"are":[79],"adapted":[80],"transformer":[83],"architecture,":[84],"progressing":[85],"Linguistic":[87],"Linearization,":[88],"which":[89,101,115,137,146,159],"optimizes":[90],"symbolic":[91],"grammars":[92],"such":[93],"as":[94],"SMILES":[95],"SELFIES,":[97],"Topological":[99],"Perception,":[100],"injects":[102],"graph":[103],"inductive":[104],"biases":[105],"adapters":[107],"projectors,":[109],"finally":[111],"Geometric":[113],"Grounding,":[114],"encodes":[116],"3D":[117],"reality":[119,151],"equivariance.":[121],"Second,":[122],"analyze":[124],"acquire":[127],"deploy":[129],"chemical":[130],"knowledge":[131],"three":[133,203],"complementary":[134],"pathways:":[135],"Internalization,":[136],"cultivates":[138],"parametric":[139],"intuition":[140],"pre-training":[142],"alignment;":[144],"Externalization,":[145],"anchors":[147],"generation":[148],"via":[152],"retrieval":[153],"tool":[155],"orchestration;":[156],"Reasoning,":[158],"further":[161],"decompose":[162],"four":[164],"strategies":[165],"spanning":[166,190],"contextual":[167],"analogy,":[168],"sequential":[169],"deduction,":[170],"strategic":[171],"planning,":[172],"introspective":[174],"refinement.":[175],"Building":[176],"on":[177],"dual-lens":[179],"framework,":[180],"map":[182],"downstream":[183],"capabilities":[184],"onto":[185],"four-level":[187],"task":[188],"hierarchy":[189],"Semantic":[191],"Translation,":[192],"Predictive":[193],"Inference,":[194],"Constrained":[195],"Generation,":[196],"Autonomous":[198],"Discovery,":[199],"identify":[202],"coupled":[204],"challenges":[205],"at":[206],"representation-cognition":[208],"interface,":[209],"outlining":[210],"research":[212],"roadmap":[213],"toward":[214],"chemically":[215],"grounded":[216],"AI":[217],"systems.":[218]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-27T00:00:00"}