{"id":"https://openalex.org/W7166879169","doi":"https://doi.org/10.18653/v1/2026.bionlp-1.22","title":"KGRxn-LLM: Knowledge Graph Enhanced Large Language Models for Molecular Reaction Reasoning","display_name":"KGRxn-LLM: Knowledge Graph Enhanced Large Language Models for Molecular Reaction Reasoning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166879169","doi":"https://doi.org/10.18653/v1/2026.bionlp-1.22"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.bionlp-1.22","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.bionlp-1.22","pdf_url":"https://aclanthology.org/2026.bionlp-1.22.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":"BioNLP 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.bionlp-1.22.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139742973","display_name":"Weichen Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weichen Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115003568","display_name":"Qiyao Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiyao Xue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139765424","display_name":"Yuyang Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuyang Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139735015","display_name":"Olexandr Isayev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olexandr Isayev","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5017141796","display_name":"Nata\u0161a Mi\u0161kov-\u017divanov","orcid":"https://orcid.org/0000-0003-1110-3403"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Natasa Miskov-Zivanov","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":0.86714012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"268","last_page":"281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.7978000044822693,"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":0.7978000044822693,"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":0.08720000088214874,"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":0.01889999955892563,"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/graph","display_name":"Graph","score":0.4553000032901764},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.4203999936580658},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.37700000405311584},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.37040001153945923},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.3560999929904938},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.34360000491142273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6470999717712402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5353999733924866},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.499099999666214},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4553000032901764},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.4203999936580658},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.37700000405311584},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3052000105381012},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.bionlp-1.22","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.bionlp-1.22","pdf_url":"https://aclanthology.org/2026.bionlp-1.22.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":"BioNLP 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.bionlp-1.22","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.bionlp-1.22","pdf_url":"https://aclanthology.org/2026.bionlp-1.22.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":"BioNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5002099871635437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166879169.pdf","grobid_xml":"https://content.openalex.org/works/W7166879169.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,7],"models":[2,122],"(LLMs)":[3],"demonstrate":[4],"strong":[5],"general":[6],"capabilities":[8],"but":[9],"remain":[10],"limited":[11,61],"in":[12,46,106],"chemical":[13,39],"reasoning,":[14],"particularly":[15],"for":[16],"tasks":[17,114],"requiring":[18],"structured,":[19],"mechanistic":[20,65],"understanding":[21],"of":[22,63,75,103],"molecular":[23,47,57],"reactions.We":[24],"present":[25],"Knowledge":[26],"Graph":[27],"Reaction":[28],"LLM":[29],"(KGRxn-LLM),":[30],"a":[31,37,73],"framework":[32],"that":[33,100],"augments":[34],"LLMs":[35,81,105],"with":[36],"hierarchical":[38],"knowledge":[40],"graph":[41],"(KG)":[42],"to":[43,79],"ground":[44],"reasoning":[45,84],"transformations":[48],"and":[49,93,95,115,126],"reaction":[50,55,90],"patterns.Existing":[51],"benchmarks":[52],"primarily":[53],"emphasize":[54],"or":[56],"fact":[58],"recall,":[59],"providing":[60],"assessment":[62],"reaction-level":[64],"reasoning.To":[66],"address":[67],"this":[68],"gap,":[69],"we":[70],"introduce":[71],"KGRxn-Bench,":[72],"benchmark":[74],"1,200":[76],"questions":[77],"designed":[78],"evaluate":[80],"on":[82,123],"reaction-centric":[83],"tasks,":[85],"including":[86],"functional":[87],"group":[88],"identification,":[89],"type":[91],"classification,":[92],"product":[94],"reagent":[96],"prediction.Experimental":[97],"results":[98],"show":[99],"our":[101],"approach":[102],"grounding":[104],"structured":[107],"KG":[108],"substantially":[109],"improves":[110],"performance":[111],"across":[112],"multiple":[113],"model":[116],"backbones,":[117],"outperforming":[118],"domain":[119],"specific":[120],"fine-tuned":[121],"KG-covered":[124],"splits":[125],"most":[127],"hold-out":[128],"splits.":[129],"1":[130]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}