{"id":"https://openalex.org/W4412888632","doi":"https://doi.org/10.18653/v1/2025.findings-acl.312","title":"LR\u00b2Bench: Evaluating Long-chain Reflective Reasoning Capabilities of Large Language Models via Constraint Satisfaction Problems","display_name":"LR\u00b2Bench: Evaluating Long-chain Reflective Reasoning Capabilities of Large Language Models via Constraint Satisfaction Problems","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888632","doi":"https://doi.org/10.18653/v1/2025.findings-acl.312"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.312","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.312","pdf_url":"https://aclanthology.org/2025.findings-acl.312.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: ACL 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.312.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101844331","display_name":"Jianghao Chen","orcid":"https://orcid.org/0000-0001-7280-9149"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianghao Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050079489","display_name":"Zhenlin Wei","orcid":"https://orcid.org/0000-0001-5172-1279"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenlin Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhenjiang Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenjiang Ren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062484867","display_name":"Ziyong Li","orcid":"https://orcid.org/0000-0002-2658-2286"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyong Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100319572","display_name":"Jiajun Zhang","orcid":"https://orcid.org/0000-0001-5293-7434"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiajun Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5175,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93064767,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6006","last_page":"6032"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9904000163078308,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9904000163078308,"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/T10028","display_name":"Topic Modeling","score":0.9871000051498413,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9797000288963318,"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/constraint-satisfaction","display_name":"Constraint satisfaction","score":0.6751612424850464},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6433789730072021},{"id":"https://openalex.org/keywords/constraint-satisfaction-problem","display_name":"Constraint satisfaction problem","score":0.6188933849334717},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5838119983673096},{"id":"https://openalex.org/keywords/chain","display_name":"Chain (unit)","score":0.5353409051895142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33052778244018555},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3204006552696228},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13799020648002625}],"concepts":[{"id":"https://openalex.org/C44616089","wikidata":"https://www.wikidata.org/wiki/Q30158686","display_name":"Constraint satisfaction","level":3,"score":0.6751612424850464},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6433789730072021},{"id":"https://openalex.org/C199622910","wikidata":"https://www.wikidata.org/wiki/Q1128326","display_name":"Constraint satisfaction problem","level":3,"score":0.6188933849334717},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5838119983673096},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.5353409051895142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33052778244018555},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3204006552696228},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13799020648002625},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.312","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.312","pdf_url":"https://aclanthology.org/2025.findings-acl.312.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: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.312","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.312","pdf_url":"https://aclanthology.org/2025.findings-acl.312.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: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888632.pdf","grobid_xml":"https://content.openalex.org/works/W4412888632.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2161128834","https://openalex.org/W2091348864","https://openalex.org/W2569549435","https://openalex.org/W2097415053","https://openalex.org/W2012141606","https://openalex.org/W1550482496","https://openalex.org/W2784687883","https://openalex.org/W2102858635","https://openalex.org/W1527777107","https://openalex.org/W2012694101"],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2,141,164],"Large":[3,14],"Reasoning":[4,66],"Models":[5,16],"(LRMs)":[6],"has":[7],"significantly":[8],"enhanced":[9],"the":[10,44,63,128,159,165],"reasoning":[11,83,167],"abilities":[12],"of":[13,46,68,95,113,151,169],"Language":[15],"(LLMs),":[17],"empowering":[18],"them":[19],"to":[20,43,61],"tackle":[21],"increasingly":[22],"complex":[23],"tasks":[24,140],"through":[25],"reflection":[26,38],"capabilities,":[27],"such":[28,37,102,132],"as":[29,103,133],"making":[30],"assumptions,":[31],"backtracking,":[32],"and":[33,106,123,135,154],"self-refinement.However,":[34],"effectively":[35],"evaluating":[36],"capabilities":[39,67,168],"remains":[40],"challenging":[41],"due":[42],"lack":[45],"appropriate":[47],"benchmarks.To":[48],"bridge":[49],"this":[50],"gap,":[51],"we":[52],"introduce":[53],"LR":[54,142],"2":[55,70,143],"Bench,":[56,144],"a":[57,110],"novel":[58],"benchmark":[59],"designed":[60],"evaluate":[62],"Long-chain":[64],"Reflective":[65],"LLMs.LR":[69],"Bench":[71],"comprises":[72],"850":[73],"samples":[74],"across":[75],"six":[76],"Constraint":[77],"Satisfaction":[78],"Problems":[79],"(CSPs)":[80],"where":[81],"reflective":[82,166],"is":[84],"crucial":[85],"for":[86,162],"deriving":[87],"solutions":[88],"that":[89,126],"meet":[90],"all":[91],"given":[92],"constraints.Each":[93],"type":[94],"task":[96],"focuses":[97],"on":[98,119],"distinct":[99],"constraint":[100],"patterns,":[101],"knowledge-based,":[104],"logical,":[105],"spatial":[107],"constraints,":[108],"providing":[109],"comprehensive":[111],"evaluation":[112,118],"diverse":[114],"problem-solving":[115],"scenarios.Our":[116],"extensive":[117],"both":[120],"conventional":[121],"LLMs":[122],"LRMs":[124],"reveals":[125],"even":[127],"most":[129],"advanced":[130],"LRMs,":[131],"DeepSeek-R1":[134],"OpenAI":[136],"o1-preview,":[137],"struggle":[138],"with":[139],"achieving":[145],"an":[146],"average":[147],"Exact":[148],"Match":[149],"score":[150],"only":[152],"20.0%":[153],"23.6%,":[155],"respectively.These":[156],"findings":[157],"underscore":[158],"significant":[160],"room":[161],"improvement":[163],"current":[170],"LLMs.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}