{"id":"https://openalex.org/W4416035959","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.55","title":"Two Steps from Hell: Compositionality on Chemical LMs","display_name":"Two Steps from Hell: Compositionality on Chemical LMs","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035959","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.55"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.55","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.55","pdf_url":"https://aclanthology.org/2025.findings-emnlp.55.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.55.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009708250","display_name":"Veronika Ganeeva","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Veronika Ganeeva","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082532694","display_name":"Kuzma Khrabrov","orcid":"https://orcid.org/0000-0002-0446-6751"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuzma Khrabrov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019867253","display_name":"Artur Kadurin","orcid":"https://orcid.org/0000-0003-1482-9365"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Artur Kadurin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5012311258","display_name":"Elena Tutubalina","orcid":"https://orcid.org/0000-0001-7936-0284"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elena Tutubalina","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":0.34077006,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1042","last_page":"1049"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11445","display_name":"Origins and Evolution of Life","score":0.14499999582767487,"subfield":{"id":"https://openalex.org/subfields/3103","display_name":"Astronomy and Astrophysics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11445","display_name":"Origins and Evolution of Life","score":0.14499999582767487,"subfield":{"id":"https://openalex.org/subfields/3103","display_name":"Astronomy and Astrophysics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10807","display_name":"Synthesis and characterization of novel inorganic/organometallic compounds","score":0.05180000141263008,"subfield":{"id":"https://openalex.org/subfields/1604","display_name":"Inorganic Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10913","display_name":"Molecular Junctions and Nanostructures","score":0.02250000089406967,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/principle-of-compositionality","display_name":"Principle of compositionality","score":0.4291999936103821},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.33550000190734863},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.32690000534057617},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.30169999599456787},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.26019999384880066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5231999754905701},{"id":"https://openalex.org/C121375916","wikidata":"https://www.wikidata.org/wiki/Q936559","display_name":"Principle of compositionality","level":2,"score":0.4291999936103821},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37709999084472656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36169999837875366},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3246000111103058},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31060001254081726},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.55","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.55","pdf_url":"https://aclanthology.org/2025.findings-emnlp.55.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.55","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.55","pdf_url":"https://aclanthology.org/2025.findings-emnlp.55.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":[{"id":"https://openalex.org/F4320324632","display_name":"Ministero dello Sviluppo Economico","ror":"https://ror.org/011z3ff80"},{"id":"https://openalex.org/F4320334801","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035959.pdf","grobid_xml":"https://content.openalex.org/works/W4416035959.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"compositionality":[3,97],"in":[4,60,98,103,112],"chemical":[5,19,28,39,87,99,202,213],"language":[6,105,203],"models":[7,67,106,163,204],"(ChemLLMs).We":[8],"introduce":[9],"STEP,":[10],"a":[11,91,196],"benchmark":[12],"with":[13,53,115,166,206],"compositional":[14,36,61],"questions":[15],"that":[16,68],"reflect":[17],"intricate":[18],"structures":[20],"and":[21,34,74,89,125,155,173,182,190],"reactions,":[22],"to":[23,43,80,122,164,215,222],"evaluate":[24,44],"models'":[25],"understanding":[26],"of":[27,84,226],"language.Our":[29],"approach":[30],"focuses":[31],"on":[32,96,147,176],"identifying":[33],"analyzing":[35],"patterns":[37],"within":[38],"data,":[40],"allowing":[41],"us":[42],"how":[45],"well":[46],"existing":[47],"LLMs":[48,88],"can":[49,209],"handle":[50],"complex":[51],"queries.Experiments":[52],"state-of-the-art":[54],"ChemLLMs":[55,145],"show":[56],"significant":[57],"performance":[58],"drops":[59],"tasks,":[62],"highlighting":[63],"the":[64,82],"need":[65],"for":[66,93],"move":[69],"beyond":[70],"pattern":[71],"recognition.By":[72],"creating":[73],"sharing":[75],"this":[76,223],"benchmark,":[77],"we":[78],"aim":[79],"enhance":[81],"development":[83],"more":[85],"capable":[86],"provide":[90],"resource":[92],"future":[94],"research":[95],"understanding.":[100],"IntroductionRecent":[101],"advances":[102],"large":[104],"(LLMs)":[107],"have":[108,161],"significantly":[109],"accelerated":[110],"progress":[111],"computational":[113],"chemistry,":[114],"applications":[116],"ranging":[117],"from":[118],"molecular":[119,167],"property":[120],"prediction":[121],"reaction":[123],"design":[124],"drug":[126],"discovery":[127],"(Schwaller":[128],"et":[129,132,136,139,152,158,187],"al.,":[130,133,137,140,153,159,188],"2018(Schwaller":[131],",":[134],"2021;;Livne":[135],"2024;Kuznetsov":[138],"2025).Domain-specific":[141],"adaptations":[142],"such":[143,178],"as":[144,179],"built":[146],"architectures":[148],"like":[149],"T5":[150],"(Raffel":[151],"2020)":[154],"LLaMA":[156],"(Touvron":[157],"2023)":[160],"enabled":[162],"interface":[165],"representations":[168],"(e.g.,":[169],"SMILES":[170],"(Weininger,":[171],"1988))":[172],"operate":[174],"effectively":[175],"datasets":[177],"ZINC-15":[180],"(Sterling":[181],"Irwin,":[183],"2015b),":[184],"PubChem":[185],"(Kim":[186],"2016),":[189],"USPTO-50KK":[191],"(Lowe,":[192],"2012).Despite":[193],"these":[194],"successes,":[195],"fundamental":[197],"question":[198],"remains":[199],"underexplored:":[200],"Can":[201],"work":[205],"compositionally?That":[207],"is,":[208],"they":[210],"combine":[211],"known":[212],"concepts":[214],"solve":[216],"*":[217],"These":[218],"authors":[219],"contributed":[220],"equally":[221],"work.The":[224],"order":[225],"author":[227],"names":[228],"was":[229],"randomly":[230],"determined.":[231]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}
