{"id":"https://openalex.org/W7138404040","doi":"https://doi.org/10.1609/aaai.v40i3.37170","title":"ARCHE: A Novel Task to Evaluate LLMs on Latent Reasoning Chain Extraction","display_name":"ARCHE: A Novel Task to Evaluate LLMs on Latent Reasoning Chain Extraction","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138404040","doi":"https://doi.org/10.1609/aaai.v40i3.37170"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i3.37170","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37170","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37170/41132","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37170/41132","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129683237","display_name":"Pengze Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Pengze Li","raw_affiliation_strings":["Artificial Intelligence Innovation and Incubation Institute of Fudan University\nShanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Innovation and Incubation Institute of Fudan University\nShanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129727193","display_name":"Jiaqi Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqi Liu","raw_affiliation_strings":["Department of Computer Science, University of North Carolina at Chapel Hill\nShanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of North Carolina at Chapel Hill\nShanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060684352","display_name":"Junchi Yu","orcid":"https://orcid.org/0000-0003-4118-3248"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Junchi Yu","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129682946","display_name":"Lihao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lihao Liu","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129676372","display_name":"Mingyu Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingyu Ding","raw_affiliation_strings":["Department of Computer Science, University of North Carolina at Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129646176","display_name":"Wanli Ouyang","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wanli Ouyang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory\nThe Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory\nThe Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129680344","display_name":"Shixiang Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shixiang Tang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory\nThe Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory\nThe Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129687665","display_name":"Xi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xi Chen","raw_affiliation_strings":["Artificial Intelligence Innovation and Incubation Institute of Fudan University\nShanghai Academy of AI for Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Innovation and Incubation Institute of Fudan University\nShanghai Academy of AI for Science","institution_ids":["https://openalex.org/I4210164862"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"3","first_page":"1900","last_page":"1908"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2856000065803528,"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/T10028","display_name":"Topic Modeling","score":0.2856000065803528,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.14949999749660492,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.12359999865293503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/deductive-reasoning","display_name":"Deductive reasoning","score":0.6309000253677368},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6309000253677368},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5756000280380249},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5738000273704529},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.4706000089645386},{"id":"https://openalex.org/keywords/abductive-reasoning","display_name":"Abductive reasoning","score":0.4625000059604645},{"id":"https://openalex.org/keywords/logical-reasoning","display_name":"Logical reasoning","score":0.4422000050544739},{"id":"https://openalex.org/keywords/completeness","display_name":"Completeness (order theory)","score":0.4269999861717224},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.4221999943256378}],"concepts":[{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.6309000253677368},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6309000253677368},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6061999797821045},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5756000280380249},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5746999979019165},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5738000273704529},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.4625000059604645},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.4269999861717224},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.4221999943256378},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.421099990606308},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.40119999647140503},{"id":"https://openalex.org/C2992562121","wikidata":"https://www.wikidata.org/wiki/Q3817808","display_name":"Scientific reasoning","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.34619998931884766},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.3441999852657318},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34060001373291016},{"id":"https://openalex.org/C3746660","wikidata":"https://www.wikidata.org/wiki/Q1068763","display_name":"Rule of inference","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C36964233","wikidata":"https://www.wikidata.org/wiki/Q7920942","display_name":"Verbal reasoning","level":3,"score":0.30149999260902405},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2711000144481659},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2651999890804291},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i3.37170","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37170","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37170/41132","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i3.37170","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37170","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37170/41132","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138404040.pdf","grobid_xml":"https://content.openalex.org/works/W7138404040.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,31,58,158,191],"(LLMs)":[3],"are":[4,24,85,168],"increasingly":[5],"used":[6],"in":[7,56,70],"scientific":[8,40,197],"domains.":[9],"While":[10],"they":[11],"can":[12],"produce":[13],"reasoning-like":[14],"content":[15,137],"via":[16],"methods":[17],"such":[18],"as":[19,88],"chain-of-thought":[20],"prompting,":[21],"these":[22],"outputs":[23],"typically":[25],"unstructured":[26],"and":[27,124,139,164,166,175,192],"informal,":[28],"obscuring":[29],"whether":[30],"truly":[32],"understand":[33],"the":[34,71,186,193],"fundamental":[35,95],"reasoning":[36,62,68,83,177,190],"paradigms":[37,69],"that":[38,157],"underpin":[39],"inference.":[41],"To":[42,102],"address":[43],"this,":[44],"we":[45,106],"introduce":[46],"a":[47,74,110,160,173,182],"novel":[48],"task":[49],"named":[50],"Latent":[51],"Reasoning":[52,75,140],"Chain":[53],"Extraction":[54],"(ARCHE),":[55],"which":[57],"must":[59],"decompose":[60],"complex":[61],"arguments":[63],"into":[64],"combinations":[65],"of":[66,73,90,93,188],"standard":[67,176],"form":[72],"Logic":[76],"Tree":[77],"(RLT).":[78],"In":[79],"an":[80],"RLT,":[81],"all":[82],"steps":[84],"explicitly":[86],"categorized":[87],"one":[89],"three":[91],"variants":[92],"Peirce\u2019s":[94],"inference":[96],"modes:":[97],"deduction,":[98],"induction,":[99],"or":[100],"abduction.":[101],"facilitate":[103],"this":[104],"task,":[105],"release":[107],"ARCHE":[108,154],"Bench,":[109],"new":[111],"benchmark":[112],"derived":[113],"from":[114],"70":[115],"Nature":[116],"Communications":[117],"articles,":[118],"including":[119],"more":[120],"than":[121],"1,900":[122],"references":[123],"38,000":[125],"viewpoints.":[126],"We":[127],"propose":[128],"two":[129],"logic-aware":[130],"evaluation":[131],"metrics:":[132],"Entity":[133],"Coverage":[134],"(EC)":[135],"for":[136,144,196],"completeness":[138],"Edge":[141],"Accuracy":[142],"(REA)":[143],"step-by-step":[145],"logical":[146],"validity.":[147],"Evaluations":[148],"on":[149,153],"10":[150],"leading":[151],"LLMs":[152],"Bench":[155],"reveal":[156],"exhibit":[159],"trade-off":[161],"between":[162,185],"REA":[163],"EC,":[165],"none":[167],"yet":[169],"able":[170],"to":[171],"extract":[172],"complete":[174],"chain.":[178],"These":[179],"findings":[180],"highlight":[181],"substantial":[183],"gap":[184],"abilities":[187],"current":[189],"rigor":[194],"required":[195],"argumentation.":[198]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}