{"id":"https://openalex.org/W7161719302","doi":"https://doi.org/10.48550/arxiv.2605.17214","title":"ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding","display_name":"ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding","publication_year":2026,"publication_date":"2026-05-17","ids":{"openalex":"https://openalex.org/W7161719302","doi":"https://doi.org/10.48550/arxiv.2605.17214"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.17214","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17214","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.17214","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136460370","display_name":"Mingyang Rao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rao, Mingyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113178971","display_name":"Kehua Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Kehua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136472021","display_name":"Zhihui Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Zhihui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108301117","display_name":"Jiangzhen Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Jiangzhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136467006","display_name":"Hao Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136454262","display_name":"Keyan Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Keyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136481256","display_name":"Huajun Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Huajun","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":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/T11948","display_name":"Machine Learning in Materials Science","score":0.7253000140190125,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.7253000140190125,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07010000199079514,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.04749999940395355,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5734999775886536},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.46880000829696655},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.3783000111579895},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.3612000048160553},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.3260999917984009},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.310699999332428},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.30239999294281006}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7092999815940857},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5734999775886536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5332000255584717},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.46880000829696655},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3889999985694885},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3612000048160553},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29589998722076416},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26989999413490295},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.17214","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17214","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.17214","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17214","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7103617787361145,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"have":[5],"revolutionized":[6],"scientific":[7],"text":[8],"processing,":[9],"they":[10],"exhibit":[11],"a":[12,29,48,81,94,117,159],"significant":[13],"capability":[14],"gap":[15],"when":[16],"interpreting":[17],"chemical":[18,65,182],"reaction":[19,127],"diagrams.":[20],"We":[21,111],"identify":[22],"two":[23],"fundamental":[24],"bottlenecks":[25],"restricting":[26],"current":[27],"systems:":[28],"Visual":[30,75,82],"Deficit,":[31],"where":[32,51],"generic":[33],"vision":[34],"encoders":[35],"struggle":[36],"to":[37,59,85,105,129,136,175],"resolve":[38],"the":[39,62,73,131],"strict":[40],"topological":[41],"connectivity":[42],"of":[43,163],"dense":[44,122],"molecular":[45],"graphs,":[46],"and":[47,125,153],"Semantic":[49],"Disconnect,":[50],"standard":[52],"linear":[53],"strings,":[54],"such":[55],"as":[56],"SMILES,":[57],"fail":[58],"effectively":[60],"activate":[61],"model's":[63],"latent":[64],"reasoning.":[66,137],"To":[67],"bridge":[68],"these":[69],"gaps,":[70],"we":[71],"propose":[72],"Chemical":[74],"Activation":[76],"(ChemVA)":[77],"framework,":[78],"which":[79],"employs":[80],"Anchor":[83],"mechanism":[84],"ground":[86],"functional":[87],"groups":[88],"via":[89],"hybrid-granularity":[90],"detection,":[91],"followed":[92],"by":[93],"semantic":[95,154],"alignment":[96],"approach":[97,114],"that":[98,143],"translates":[99],"visual":[100,152],"features":[101],"into":[102],"entity":[103],"names":[104],"maximize":[106],"knowledge":[107],"activation":[108],"in":[109,180],"LLMs.":[110],"evaluate":[112,130],"our":[113,156],"on":[115,140],"OCRD-Bench,":[116],"newly":[118],"constructed":[119],"dataset":[120],"featuring":[121],"visual-semantic":[123],"contexts":[124],"comprehensive":[126],"coverage":[128],"full":[132],"spectrum":[133],"from":[134],"recognition":[135,148],"Extensive":[138],"experiments":[139],"OCRD-Bench":[141],"demonstrate":[142],"ChemVA":[144],"achieves":[145],"92.0%":[146],"structural":[147],"accuracy.":[149],"By":[150],"bridging":[151],"bottlenecks,":[155],"framework":[157],"delivers":[158],"consistent":[160],"performance":[161],"gain":[162],"approximately":[164],"20":[165],"percentage":[166],"points":[167],"across":[168],"9":[169],"diverse":[170],"LLMs,":[171],"enabling":[172],"open-weight":[173],"models":[174],"rival":[176],"proprietary":[177],"SOTA":[178],"systems":[179],"complex":[181],"reasoning":[183],"tasks.":[184]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-20T00:00:00"}