{"id":"https://openalex.org/W4415428900","doi":"https://doi.org/10.3233/faia250890","title":"CP-Bench: Evaluating Large Language Models for Constraint Modelling","display_name":"CP-Bench: Evaluating Large Language Models for Constraint Modelling","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428900","doi":"https://doi.org/10.3233/faia250890"},"language":null,"primary_location":{"id":"doi:10.3233/faia250890","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250890","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia250890","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120092319","display_name":"Kostis Michailidis","orcid":null},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Kostis Michailidis","raw_affiliation_strings":["Department of Computer Science, KU Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090844108","display_name":"Dimosthenis C. Tsouros","orcid":"https://orcid.org/0000-0002-3040-0959"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Dimos Tsouros","raw_affiliation_strings":["Department of Computer Science, KU Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041230402","display_name":"Tias Guns","orcid":"https://orcid.org/0000-0002-2156-2155"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Tias Guns","raw_affiliation_strings":["Department of Computer Science, KU Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99464096"],"apc_list":null,"apc_paid":null,"fwci":2.9081,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9296875,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"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/T10703","display_name":"Business Process Modeling and Analysis","score":0.9686999917030334,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.9686999917030334,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/constraint-programming","display_name":"Constraint programming","score":0.7146000266075134},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6435999870300293},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.6315000057220459},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.527400016784668},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5213000178337097},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5059000253677368},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.47369998693466187},{"id":"https://openalex.org/keywords/constraint-satisfaction","display_name":"Constraint satisfaction","score":0.47269999980926514}],"concepts":[{"id":"https://openalex.org/C173404611","wikidata":"https://www.wikidata.org/wiki/Q528588","display_name":"Constraint programming","level":3,"score":0.7146000266075134},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6718000173568726},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6435999870300293},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.6315000057220459},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.527400016784668},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5213000178337097},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5059000253677368},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.47369998693466187},{"id":"https://openalex.org/C44616089","wikidata":"https://www.wikidata.org/wiki/Q30158686","display_name":"Constraint satisfaction","level":3,"score":0.47269999980926514},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4350000023841858},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.41530001163482666},{"id":"https://openalex.org/C176783269","wikidata":"https://www.wikidata.org/wiki/Q5164378","display_name":"Constraint logic programming","level":4,"score":0.39750000834465027},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34200000762939453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33799999952316284},{"id":"https://openalex.org/C199622910","wikidata":"https://www.wikidata.org/wiki/Q1128326","display_name":"Constraint satisfaction problem","level":3,"score":0.329800009727478},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32820001244544983},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.30469998717308044},{"id":"https://openalex.org/C56086750","wikidata":"https://www.wikidata.org/wiki/Q6042592","display_name":"Integer programming","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26579999923706055},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/faia250890","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250890","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:lirias2repo.kuleuven.be:20.500.12942/773939","is_oa":false,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/773939","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"28th European Conference on Artificial Intelligence (ECAI), Bologna, Italy, 25-30 October 2025","raw_type":"info:eu-repo/semantics/acceptedVersion"}],"best_oa_location":{"id":"doi:10.3233/faia250890","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250890","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Constraint":[0],"Programming":[1],"(CP)":[2],"is":[3,21],"widely":[4],"used":[5],"to":[6,23,31,44,64,179],"solve":[7],"combinatorial":[8,46,97],"problems,":[9],"but":[10],"its":[11],"core":[12],"process,":[13],"namely":[14],"constraint":[15,51,59,119,134],"modelling,":[16],"requires":[17],"significant":[18],"expertise":[19],"and":[20,114,124,142,166],"considered":[22],"be":[24],"a":[25,87,92,154],"bottleneck":[26],"for":[27,58,106,131],"wider":[28],"adoption.":[29],"Aiming":[30],"alleviate":[32],"this":[33,82,112,182],"bottleneck,":[34],"recent":[35],"studies":[36],"have":[37],"explored":[38],"using":[39],"Large":[40],"Language":[41],"Models":[42],"(LLMs)":[43],"transform":[45],"problem":[47],"descriptions":[48],"into":[49],"executable":[50],"models.":[52],"However,":[53],"the":[54,74,101,116,126,146,162],"existing":[55],"evaluation":[56],"datasets":[57],"modelling":[60,120,127,135,152],"are":[61],"often":[62],"limited":[63],"small,":[65],"homogeneous,":[66],"or":[67],"domain-specific":[68],"instances,":[69],"which":[70,137,173],"do":[71],"not":[72],"capture":[73],"diversity":[75],"of":[76,95,118,129,164],"real-world":[77],"scenarios.":[78],"This":[79],"work":[80],"addresses":[81],"gap":[83],"by":[84],"introducing":[85],"CP-Bench,":[86],"novel":[88],"benchmark":[89],"that":[90],"includes":[91],"diverse":[93],"set":[94],"well-known":[96],"problems":[98],"sourced":[99],"from":[100],"CP":[102,109],"community,":[103],"structured":[104],"explicitly":[105],"evaluating":[107],"LLM-driven":[108],"modelling.":[110],"With":[111],"dataset,":[113],"given":[115],"variety":[117],"frameworks,":[121],"we":[122,159],"compare":[123],"evaluate":[125,161],"capabilities":[128],"LLMs":[130],"three":[132],"distinct":[133],"systems,":[136],"vary":[138],"in":[139],"abstraction":[140],"level":[141],"underlying":[143],"syntax.":[144],"Notably,":[145],"results":[147],"show":[148],"higher":[149],"performance":[150],"when":[151],"with":[153],"high-level":[155],"Python-based":[156],"framework.":[157],"Additionally,":[158],"systematically":[160],"use":[163],"prompt-based":[165],"inference-time":[167],"compute":[168],"methods":[169],"across":[170],"different":[171],"LLMs,":[172],"further":[174],"increase":[175],"accuracy,":[176],"reaching":[177],"up":[178],"70%":[180],"on":[181],"highly":[183],"challenging":[184],"benchmark.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-13T07:31:44.756512","created_date":"2025-10-24T00:00:00"}