{"id":"https://openalex.org/W7203864446","doi":"https://doi.org/10.48550/arxiv.2608.18940","title":"Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis","display_name":"Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis","publication_year":2026,"publication_date":"2026-08-19","ids":{"openalex":"https://openalex.org/W7203864446","doi":"https://doi.org/10.48550/arxiv.2608.18940"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.18940","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.18940","pdf_url":"https://arxiv.org/pdf/2608.18940","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.18940","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036803601","display_name":"Bogdan A. Zagribelnyy","orcid":"https://orcid.org/0000-0003-3799-2720","observed_orcids":["https://orcid.org/0000-0003-3799-2720"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zagribelnyy, Bogdan","raw_affiliation_strings":["Insilico Medicine AI Limited , Abu Dhabi , UAE,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insilico Medicine AI Limited , Abu Dhabi , UAE,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030842718","display_name":"Ivan S. Ilin","orcid":"https://orcid.org/0000-0002-3612-393X","observed_orcids":["https://orcid.org/0000-0002-3612-393X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ilin, Ivan","raw_affiliation_strings":["Insilico Medicine AI Limited , Abu Dhabi , UAE,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insilico Medicine AI Limited , Abu Dhabi , UAE,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008193304","display_name":"Nikita Bondarev","orcid":"https://orcid.org/0009-0003-0395-3659","observed_orcids":["https://orcid.org/0009-0003-0395-3659"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bondarev, Nikita","raw_affiliation_strings":["Insilico Medicine AI Limited , Abu Dhabi , UAE,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insilico Medicine AI Limited , Abu Dhabi , UAE,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128186584","display_name":"Maksim Kuznetsov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuznetsov, Maksim","raw_affiliation_strings":["Insilico Medicine Canada Inc. , Montreal , Quebec , Canada,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insilico Medicine Canada Inc. , Montreal , Quebec , Canada,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082723540","display_name":"Mathieu Reymond","orcid":"https://orcid.org/0000-0002-6735-6752","observed_orcids":["https://orcid.org/0000-0002-6735-6752"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reymond, Mathieu","raw_affiliation_strings":["Insilico Medicine Canada Inc. , Montreal , Quebec , Canada,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insilico Medicine Canada Inc. , Montreal , Quebec , Canada,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083789823","display_name":"Vladimir Aladinskiy","orcid":"https://orcid.org/0000-0002-3976-3991","observed_orcids":["https://orcid.org/0000-0002-3976-3991"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aladinskiy, Vladimir","raw_affiliation_strings":["Insilico Medicine AI Limited , Abu Dhabi , UAE,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insilico Medicine AI Limited , Abu Dhabi , UAE,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113161674","display_name":"Alex Aliper","orcid":"https://orcid.org/0000-0002-4363-0710","observed_orcids":["https://orcid.org/0000-0002-4363-0710"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aliper, Alex","raw_affiliation_strings":["Insilico Medicine AI Limited , Abu Dhabi , UAE,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insilico Medicine AI Limited , Abu Dhabi , UAE,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140301156","display_name":"Alex Zhavoronkov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhavoronkov, Alex","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":true,"cited_by_count":2,"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":0.8403000235557556,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.8403000235557556,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.045899998396635056,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.020400000736117363,"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/large-language-models","display_name":"large language models","score":0.8199999928474426},{"id":"https://openalex.org/keywords/reaction-prediction","display_name":"chemical reaction prediction","score":0.7039999961853027},{"id":"https://openalex.org/keywords/out-of-distribution-evaluation","display_name":"out-of-distribution evaluation","score":0.6959999799728394},{"id":"https://openalex.org/keywords/computer-aided-synthesis-planning","display_name":"computer-aided synthesis planning","score":0.921999990940094}],"concepts":[{"id":"https://openalex.org/C42437451","wikidata":"https://www.wikidata.org/wiki/Q902227","display_name":"Retrosynthetic analysis","level":3,"score":0.7149999737739563},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6075000166893005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6004999876022339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5874000191688538},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.565500020980835},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5533000230789185},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49219998717308044},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43459999561309814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3864000141620636},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.33480000495910645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3334999978542328},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.28769999742507935},{"id":"https://openalex.org/C189645446","wikidata":"https://www.wikidata.org/wiki/Q350865","display_name":"Mirroring","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.258899986743927},{"id":"https://openalex.org/C2780589192","wikidata":"https://www.wikidata.org/wiki/Q7285140","display_name":"Raising (metalworking)","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C61123122","wikidata":"https://www.wikidata.org/wiki/Q281287","display_name":"Politeness","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.18940","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.18940","pdf_url":"https://arxiv.org/pdf/2608.18940","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.18940","doi":"https://doi.org/10.48550/arxiv.2608.18940","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.18940","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.18940","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.18940","pdf_url":"https://arxiv.org/pdf/2608.18940","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203864446.pdf","grobid_xml":"https://content.openalex.org/works/W7203864446.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W4382240123","https://openalex.org/W4391631327","https://openalex.org/W4406093460","https://openalex.org/W4416982472","https://openalex.org/W4417006854","https://openalex.org/W7127380112","https://openalex.org/W7127611024","https://openalex.org/W7130402983"],"related_works":["https://openalex.org/W7127611024","https://openalex.org/W7125521328","https://openalex.org/W7137315308","https://openalex.org/W7167623644","https://openalex.org/W4414880305","https://openalex.org/W7221774268","https://openalex.org/W7166818745","https://openalex.org/W4417182937","https://openalex.org/W7223049615","https://openalex.org/W7171706104"],"abstract_inverted_index":{"Single-step":[0],"retrosynthesis":[1,99],"is":[2,15],"a":[3,32,109],"central":[4],"component":[5],"of":[6,51,84],"computer-aided":[7],"synthesis":[8,117],"planning,":[9],"yet":[10],"its":[11],"intrinsically":[12],"one-to-many":[13],"nature":[14],"poorly":[16],"captured":[17],"by":[18],"single-answer":[19],"evaluation":[20],"and":[21,35,69,90],"benchmarking":[22],"protocols.":[23],"To":[24],"address":[25],"this,":[26],"we":[27],"introduce":[28],"Top-K":[29],"prompting":[30],"as":[31,108],"robust":[33,114],"training":[34,107],"inference":[36],"paradigm":[37],"to":[38,56],"better":[39],"capture":[40],"diverse,":[41],"plausible":[42],"reaction":[43,85,95],"predictions.":[44],"We":[45],"compile":[46],"CREED-CCV-2+USPTO-XL,":[47],"an":[48],"ultra-large-scale":[49],"dataset":[50],"~45.6":[52],"million":[53],"verified":[54],"reactions":[55],"train":[57],"the":[58,78],"C3LM":[59],"(Chemistry":[60],"Constraint-Consistent":[61],"Language":[62],"Model).":[63],"By":[64],"integrating":[65],"fine-tuning":[66],"with":[67],"ChemCensor-based":[68],"novelty-oriented":[70],"rewards,":[71],"our":[72,102],"model":[73],"achieves":[74],"state-of-the-art":[75],"performance":[76],"on":[77],"OOD":[79],"URSA-expert-2026":[80],"benchmark.":[81],"Further":[82],"analysis":[83],"uniqueness":[86],"shows":[87],"that":[88],"LLMs":[89],"conventional":[91],"models":[92],"explore":[93],"complementary":[94],"spaces,":[96],"motivating":[97],"ensemble-based":[98],"systems.":[100],"Overall,":[101],"results":[103],"establish":[104],"Top-K,":[105],"plausibility-aware":[106],"practical":[110],"new":[111],"direction":[112],"for":[113],"future":[115],"LLM-based":[116],"planning.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-22T00:00:00"}