{"id":"https://openalex.org/W4412886813","doi":"https://doi.org/10.18653/v1/2025.acl-long.79","title":"MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation Dataset","display_name":"MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation Dataset","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886813","doi":"https://doi.org/10.18653/v1/2025.acl-long.79"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.79","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.79","pdf_url":"https://aclanthology.org/2025.acl-long.79.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.79.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100601726","display_name":"Weiqi Wang","orcid":"https://orcid.org/0000-0002-1617-9805"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Weiqi Wang","raw_affiliation_strings":["Department of Computer Science and Engineering , HKUST , Hong Kong SAR , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , HKUST , Hong Kong SAR , China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020880385","display_name":"Yangqiu Song","orcid":"https://orcid.org/0000-0002-7818-6090"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yangqiu Song","raw_affiliation_strings":["Department of Computer Science and Engineering , HKUST , Hong Kong SAR , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , HKUST , Hong Kong SAR , China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I200769079"],"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":null,"issue":null,"first_page":"1568","last_page":"1596"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9944000244140625,"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":0.9944000244140625,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9836000204086304,"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/benchmarking","display_name":"Benchmarking","score":0.8142184019088745},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7257287502288818},{"id":"https://openalex.org/keywords/mars-exploration-program","display_name":"Mars Exploration Program","score":0.7067854404449463},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6547338962554932},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5008440017700195},{"id":"https://openalex.org/keywords/metaphysics","display_name":"Metaphysics","score":0.4916017949581146},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48669081926345825},{"id":"https://openalex.org/keywords/astrobiology","display_name":"Astrobiology","score":0.1893017590045929},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.11683228611946106},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10941734910011292},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09160667657852173},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.08099853992462158}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8142184019088745},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7257287502288818},{"id":"https://openalex.org/C83260615","wikidata":"https://www.wikidata.org/wiki/Q6773121","display_name":"Mars Exploration Program","level":2,"score":0.7067854404449463},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6547338962554932},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5008440017700195},{"id":"https://openalex.org/C182744844","wikidata":"https://www.wikidata.org/wiki/Q35277","display_name":"Metaphysics","level":2,"score":0.4916017949581146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48669081926345825},{"id":"https://openalex.org/C87355193","wikidata":"https://www.wikidata.org/wiki/Q411","display_name":"Astrobiology","level":1,"score":0.1893017590045929},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.11683228611946106},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10941734910011292},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09160667657852173},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.08099853992462158},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.79","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.79","pdf_url":"https://aclanthology.org/2025.acl-long.79.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-168655","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-168655","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.79","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.79","pdf_url":"https://aclanthology.org/2025.acl-long.79.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886813.pdf","grobid_xml":"https://content.openalex.org/works/W4412886813.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W2112883198"],"abstract_inverted_index":{"To":[0],"enable":[1],"Large":[2],"Language":[3],"Models":[4],"(LLMs)":[5],"to":[6,23,47,103],"function":[7],"as":[8,84,90],"conscious":[9],"agents":[10],"with":[11,63,69,81,136],"generalizable":[12],"reasoning":[13,80,112,180],"capabilities,":[14],"it":[15],"is":[16],"crucial":[17],"that":[18,145,169],"they":[19],"possess":[20],"the":[21,48,64,95,113,163],"ability":[22,43],"comprehend":[24],"situational":[25,70,128],"changes":[26,54,83,117,132],"(transitions)":[27],"in":[28,55,111,118,133,149],"distribution":[29],"triggered":[30],"by":[31,123,131],"environmental":[32],"factors":[33],"or":[34],"actions":[35],"from":[36],"other":[37],"agents.Despite":[38],"its":[39],"fundamental":[40],"significance,":[41],"this":[42,150],"remains":[44],"underexplored":[45],"due":[46],"complexity":[49],"of":[50,66,79,115,139,165],"modeling":[51],"infinite":[52],"possible":[53],"an":[56],"event":[57],"and":[58,126,142,167,183],"their":[59],"associated":[60],"distributions,":[61],"coupled":[62],"lack":[65],"benchmark":[67],"data":[68,182],"transitions.Addressing":[71],"these":[72],"gaps,":[73],"we":[74],"propose":[75],"a":[76,85],"novel":[77],"formulation":[78],"distributional":[82],"three-step":[86],"discriminative":[87],"process,":[88],"termed":[89],"MetAphysical":[91],"ReaSoning.We":[92],"then":[93],"introduce":[94],"first-ever":[96],"benchmark,":[97],"MARS,":[98],"comprising":[99],"three":[100,147],"tasks":[101,106,148],"corresponding":[102],"each":[104],"step.These":[105],"systematically":[107],"assess":[108],"LLMs'":[109],"capabilities":[110],"plausibility":[114],"(i)":[116],"actions,":[119,125],"(ii)":[120],"states":[121],"caused":[122],"changed":[124],"(iii)":[127],"transitions":[129],"driven":[130],"action.Extensive":[134],"evaluations":[135],"20":[137],"(L)LMs":[138],"varying":[140],"sizes":[141],"methods":[143],"indicate":[144],"all":[146],"process":[151],"pose":[152],"significant":[153],"challenges,":[154],"even":[155],"after":[156],"fine-tuning.Further":[157],"analyses":[158],"reveal":[159],"potential":[160],"causes":[161],"for":[162],"underperformance":[164],"LLMs":[166],"demonstrate":[168],"pre-training":[170],"on":[171],"largescale":[172],"conceptualization":[173],"taxonomies":[174],"can":[175],"potentially":[176],"enhance":[177],"LMs'":[178],"metaphysical":[179],"capabilities.Our":[181],"models":[184],"are":[185],"publicly":[186],"accessible":[187],"at":[188],"https://github.":[189]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}