{"id":"https://openalex.org/W7164741407","doi":"https://doi.org/10.5715/jnlp.33.630","title":"AnaToM: A Dataset Generation Framework for Evaluating Theory of Mind Reasoning Toward Anatomy of Difficulty Through Structurally Controlled Story Generation","display_name":"AnaToM: A Dataset Generation Framework for Evaluating Theory of Mind Reasoning Toward Anatomy of Difficulty Through Structurally Controlled Story Generation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7164741407","doi":"https://doi.org/10.5715/jnlp.33.630"},"language":"en","primary_location":{"id":"doi:10.5715/jnlp.33.630","is_oa":true,"landing_page_url":"https://doi.org/10.5715/jnlp.33.630","pdf_url":"https://www.jstage.jst.go.jp/article/jnlp/33/2/33_630/_pdf","source":{"id":"https://openalex.org/S4210212357","display_name":"Journal of Natural Language Processing","issn_l":"1340-7619","issn":["1340-7619","2185-8314"],"is_oa":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Natural Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/jnlp/33/2/33_630/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109667923","display_name":"Jundai Suzuki","orcid":null},"institutions":[{"id":"https://openalex.org/I165522056","display_name":"Tokyo Denki University","ror":"https://ror.org/01pa62v70","country_code":"JP","type":"education","lineage":["https://openalex.org/I165522056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jundai Suzuki","raw_affiliation_strings":["Tokyo Denki University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Denki University","institution_ids":["https://openalex.org/I165522056"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107544618","display_name":"Ryoma Ishigaki","orcid":null},"institutions":[{"id":"https://openalex.org/I165522056","display_name":"Tokyo Denki University","ror":"https://ror.org/01pa62v70","country_code":"JP","type":"education","lineage":["https://openalex.org/I165522056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryoma Ishigaki","raw_affiliation_strings":["Tokyo Denki University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Denki University","institution_ids":["https://openalex.org/I165522056"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113916911","display_name":"Eisaku Maeda","orcid":null},"institutions":[{"id":"https://openalex.org/I165522056","display_name":"Tokyo Denki University","ror":"https://ror.org/01pa62v70","country_code":"JP","type":"education","lineage":["https://openalex.org/I165522056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Eisaku Maeda","raw_affiliation_strings":["Tokyo Denki University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Denki University","institution_ids":["https://openalex.org/I165522056"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165522056"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62672666,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"2","first_page":"630","last_page":"657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11431","display_name":"Action Observation and Synchronization","score":0.20489999651908875,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11431","display_name":"Action Observation and Synchronization","score":0.20489999651908875,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10656","display_name":"Child and Animal Learning Development","score":0.0940999984741211,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.04149999842047691,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/theory-of-mind","display_name":"Theory of mind","score":0.3353999853134155},{"id":"https://openalex.org/keywords/deductive-reasoning","display_name":"Deductive reasoning","score":0.2919999957084656},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.26179999113082886}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5367000102996826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46480000019073486},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.4530999958515167},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.36169999837875366},{"id":"https://openalex.org/C2779560602","wikidata":"https://www.wikidata.org/wiki/Q639219","display_name":"Theory of mind","level":3,"score":0.3353999853134155},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3165999948978424},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.2721000015735626},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5715/jnlp.33.630","is_oa":true,"landing_page_url":"https://doi.org/10.5715/jnlp.33.630","pdf_url":"https://www.jstage.jst.go.jp/article/jnlp/33/2/33_630/_pdf","source":{"id":"https://openalex.org/S4210212357","display_name":"Journal of Natural Language Processing","issn_l":"1340-7619","issn":["1340-7619","2185-8314"],"is_oa":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Natural Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.5715/jnlp.33.630","is_oa":true,"landing_page_url":"https://doi.org/10.5715/jnlp.33.630","pdf_url":"https://www.jstage.jst.go.jp/article/jnlp/33/2/33_630/_pdf","source":{"id":"https://openalex.org/S4210212357","display_name":"Journal of Natural Language Processing","issn_l":"1340-7619","issn":["1340-7619","2185-8314"],"is_oa":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Natural Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7164741407.pdf","grobid_xml":"https://content.openalex.org/works/W7164741407.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Evaluating":[0],"Theory":[1],"of":[2,14,21,35,52,60,85,99,114,126,141,155],"Mind":[3],"(ToM)":[4],"in":[5,87,104,118,159],"Large":[6],"Language":[7],"Models":[8],"(LLMs)":[9],"is":[10,68],"an":[11,83],"important":[12],"area":[13],"research":[15],"for":[16,77,136],"understanding":[17],"the":[18,30,38,58,97,102,110,138,153],"social":[19],"intelligence":[20],"artificial":[22],"intelligence.":[23],"Recent":[24],"ToM":[25,61,78,88,117],"benchmarks":[26],"have":[27],"significantly":[28],"enhanced":[29],"complexity,":[31],"comprehensiveness,":[32],"and":[33,101,112],"practicality":[34],"evaluations.However,":[36],"while":[37],"focus":[39],"has":[40],"been":[41],"on":[42],"constructing":[43],"\u201cmore":[44,47],"difficult\u201d":[45],"or":[46],"comprehensive\u201d":[48],"tasks,":[49],"systematic":[50,134],"analysis":[51],"structural":[53,93,139],"factors":[54,115],"that":[55,151],"inherently":[56],"determine":[57],"difficulty":[59],"reasoning,":[62,89],"i.e.,":[63],"\u201cwhat\u201d":[64],"makes":[65],"reasoning":[66,128,143],"difficult,":[67],"insufficient.Hence,":[69],"we":[70],"propose":[71],"a":[72,105,122,133,147],"new":[73],"dataset":[74],"generation":[75],"framework":[76,131],"evaluation,":[79],"named":[80],"AnaToM.To":[81],"realize":[82],"\u201canatomy":[84],"difficulty\u201d":[86],"AnaToM":[90],"strictly":[91],"controls":[92],"parameters":[94],"such":[95],"as":[96],"number":[98],"entities":[100],"timeline":[103],"story.This":[106],"parameter":[107],"control":[108],"enables":[109],"isolation":[111],"identification":[113],"affecting":[116],"LLMs,":[119],"thereby":[120],"enabling":[121],"more":[123],"precise":[124],"examination":[125],"their":[127],"mechanisms.The":[129],"proposed":[130],"provides":[132],"methodology":[135],"diagnosing":[137],"limits":[140],"LLM":[142],"abilities,":[144],"thus":[145],"offering":[146],"foundational":[148],"diagnostic":[149],"baseline":[150],"complements":[152],"evaluation":[154],"broader":[156],"sociocognitive":[157],"capabilities":[158],"future":[160],"benchmark":[161],"designs.":[162]},"counts_by_year":[],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2026-06-15T00:00:00"}