{"id":"https://openalex.org/W4406354200","doi":"https://doi.org/10.1109/tg.2025.3529117","title":"BenchING: A Benchmark for Evaluating Large Language Models in Following Structured Output Format Instruction in Text-Based Narrative Game Tasks","display_name":"BenchING: A Benchmark for Evaluating Large Language Models in Following Structured Output Format Instruction in Text-Based Narrative Game Tasks","publication_year":2025,"publication_date":"2025-01-14","ids":{"openalex":"https://openalex.org/W4406354200","doi":"https://doi.org/10.1109/tg.2025.3529117"},"language":"en","primary_location":{"id":"doi:10.1109/tg.2025.3529117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2025.3529117","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088392357","display_name":"Pittawat Taveekitworachai","orcid":"https://orcid.org/0000-0002-6824-2634"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Pittawat Taveekitworachai","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Ritsumeikan University, Osaka, Japan"],"raw_orcid":"https://orcid.org/0000-0002-6824-2634","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Engineering, Ritsumeikan University, Osaka, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071723538","display_name":"Mury F. Dewantoro","orcid":"https://orcid.org/0009-0002-1967-8607"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mury F. Dewantoro","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Ritsumeikan University, Osaka, Japan"],"raw_orcid":"https://orcid.org/0009-0002-1967-8607","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Engineering, Ritsumeikan University, Osaka, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083477129","display_name":"\u4e00\u592b \u677e\u4e0b","orcid":"https://orcid.org/0009-0002-0863-6276"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi Xia","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Ritsumeikan University, Osaka, Japan"],"raw_orcid":"https://orcid.org/0009-0002-0863-6276","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Engineering, Ritsumeikan University, Osaka, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094087465","display_name":"Pratch Suntichaikul","orcid":null},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Pratch Suntichaikul","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Ritsumeikan University, Osaka, Japan"],"raw_orcid":"https://orcid.org/0009-0005-9803-5408","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Engineering, Ritsumeikan University, Osaka, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051359789","display_name":"Ruck Thawonmas","orcid":"https://orcid.org/0000-0001-9001-5828"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ruck Thawonmas","raw_affiliation_strings":["College of Information Science and Engineering, Ritsumeikan University, Osaka, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9001-5828","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ritsumeikan University, Osaka, Japan","institution_ids":["https://openalex.org/I135768898"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I135768898"],"apc_list":null,"apc_paid":null,"fwci":7.9571,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96600634,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"17","issue":"3","first_page":"665","last_page":"675"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10731","display_name":"Educational Games and Gamification","score":0.9753000140190125,"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"}},"topics":[{"id":"https://openalex.org/T10731","display_name":"Educational Games and Gamification","score":0.9753000140190125,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9404000043869019,"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":0.9365000128746033,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8084005117416382},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.7740490436553955},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7409766912460327},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.508484959602356},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.44220903515815735},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4115193784236908},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.3762293756008148},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35048389434814453},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3380310535430908},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20288968086242676},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1646723747253418}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8084005117416382},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.7740490436553955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7409766912460327},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.508484959602356},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.44220903515815735},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4115193784236908},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.3762293756008148},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35048389434814453},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3380310535430908},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20288968086242676},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1646723747253418},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tg.2025.3529117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2025.3529117","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G7597442563","display_name":"Comprehensive Research on a Situational Learning Environment for Japanese Culture Through Virtual Space","funder_award_id":"23K20189","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W4308641634","https://openalex.org/W4360995249","https://openalex.org/W4363651325","https://openalex.org/W4363651348","https://openalex.org/W4385571232","https://openalex.org/W4385572460","https://openalex.org/W4388019306","https://openalex.org/W4388019311","https://openalex.org/W4389109194","https://openalex.org/W4389111287","https://openalex.org/W4389315156","https://openalex.org/W4393146966","https://openalex.org/W4396819036","https://openalex.org/W4401042866","https://openalex.org/W4402671569","https://openalex.org/W4404783034","https://openalex.org/W4407661798"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"In":[0,122],"this":[1,63],"article,":[2],"we":[3,93,124,174],"present":[4],"BenchING,":[5],"a":[6,59,143,176],"new":[7],"benchmark":[8],"for":[9,53,97,152,196],"evaluating":[10,62],"large":[11],"language":[12],"models":[13],"(LLMs)":[14],"on":[15,113,119],"their":[16,98,153],"ability":[17,32,99,154],"to":[18,33,36,75,100,136,155,170,179],"follow":[19],"structured":[20,51],"output":[21,37],"format":[22],"instructions":[23],"in":[24,38,46,61,68],"text-based":[25,108],"procedural":[26],"content":[27,159],"generation":[28],"(PCG)":[29],"tasks.":[30,110,121],"The":[31],"condition":[34],"LLMs":[35,77,96,118,135,151,163],"specified":[39],"formats":[40],"proves":[41],"useful,":[42],"as":[43],"downstream":[44],"components":[45],"LLM-integrated":[47],"games":[48,80],"often":[49],"require":[50],"outputs":[52,104],"exchanging":[54],"information.":[55],"However,":[56],"there":[57],"is":[58],"gap":[60],"aspect":[64],"of":[65,90,116,150,183],"LLMs,":[66],"especially":[67],"narrative":[69],"PCG":[70,109],"tasks,":[71],"making":[72],"it":[73],"difficult":[74],"select":[76],"and":[78,130,192],"design":[79],"or":[81],"applications":[82],"integrating":[83],"these":[84,117,120,138],"LLMs.":[85],"To":[86],"demonstrate":[87],"the":[88,114,181,184],"potential":[89],"our":[91,189],"benchmark,":[92],"evaluate":[94],"nine":[95],"generate":[101],"parseable":[102],"formatted":[103,158],"using":[105,160],"five":[106],"selected":[107],"We":[111,140,187],"report":[112],"performance":[115],"addition,":[123],"categorize":[125],"more":[126],"detailed":[127],"error":[128],"types":[129],"propose":[131],"solutions":[132],"by":[133],"utilizing":[134],"fix":[137,156],"errors.":[139],"also":[141],"conduct":[142],"scaling":[144],"study,":[145],"investigating":[146],"an":[147],"emergent":[148],"point":[149],"malformed":[157],"eight":[161],"quantized":[162],"with":[164],"varying":[165],"original":[166],"sizes":[167],"from":[168],"0.62":[169],"72.3":[171],"B.":[172],"Furthermore,":[173],"perform":[175],"qualitative":[177],"study":[178],"assess":[180],"quality":[182],"generated":[185],"content.":[186],"make":[188],"source":[190],"code":[191],"raw":[193],"data":[194],"available":[195],"future":[197],"research.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
