{"id":"https://openalex.org/W4416034047","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.909","title":"BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models","display_name":"BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034047","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.909"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.909","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.909","pdf_url":"https://aclanthology.org/2025.findings-emnlp.909.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.909.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108039951","display_name":"Xu Huang","orcid":"https://orcid.org/0000-0003-4354-334X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101649969","display_name":"Wenhao Zhu","orcid":"https://orcid.org/0000-0002-0249-2817"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhao Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045240612","display_name":"Hanxu Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanxu Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101615091","display_name":"Conghui He","orcid":"https://orcid.org/0000-0001-8697-695X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Conghui He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440407","display_name":"Lei Li","orcid":"https://orcid.org/0000-0003-3095-9776"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102865824","display_name":"Shujian Huang","orcid":"https://orcid.org/0000-0003-4869-0832"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shujian Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5113498194","display_name":"Fei Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16751","last_page":"16774"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.13940000534057617,"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":0.13940000534057617,"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":0.12960000336170197,"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/T13629","display_name":"Text Readability and Simplification","score":0.0820000022649765,"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/suite","display_name":"Suite","score":0.521399974822998},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.28060001134872437},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.26989999413490295},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.26899999380111694},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.2662000060081482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6886000037193298},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.521399974822998},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4569999873638153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4007999897003174},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3142000138759613},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26579999923706055},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2574999928474426},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.909","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.909","pdf_url":"https://aclanthology.org/2025.findings-emnlp.909.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.909","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.909","pdf_url":"https://aclanthology.org/2025.findings-emnlp.909.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034047.pdf","grobid_xml":"https://content.openalex.org/works/W4416034047.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"multilingual":[1,45,106,119],"benchmarks":[2,13],"focus":[3],"primarily":[4],"on":[5,80],"language":[6,21,120],"understanding":[7],"tasks.There":[8],"is":[9,66],"a":[10,43,104,110],"lack":[11],"of":[12,19,85,118],"to":[14,52,114],"measure":[15],"comprehensive":[16,105],"critical":[17],"capabilities":[18,87],"large":[20],"models":[22],"(LLMs)":[23],"across":[24,57,88],"diverse":[25,50],"languages,":[26,89],"including":[27],"instruction":[28],"following,":[29],"reasoning,":[30],"code":[31,125],"generation,":[32],"and":[33,124],"long":[34],"context":[35],"understanding.To":[36],"bridge":[37],"this":[38],"gap,":[39],"we":[40],"develop":[41],"BenchMAX,":[42],"multiway":[44],"benchmark":[46],"that":[47,94],"covers":[48],"10":[49],"tasks,":[51],"evaluate":[53],"LLMs'":[54],"general":[55],"abilities":[56],"many":[58],"languages.To":[59],"ensure":[60],"high":[61],"data":[62],"quality,":[63],"each":[64],"sample":[65],"post-edited":[67],"by":[68],"three":[69],"native":[70],"annotators":[71],"after":[72],"machine-translating":[73],"from":[74],"English":[75],"into":[76],"16":[77],"languages.Extensive":[78],"experiments":[79],"BenchMAX":[81],"reveal":[82],"uneven":[83],"utilization":[84],"core":[86],"emphasizing":[90],"the":[91,116],"performance":[92],"gaps":[93],"scaling":[95],"model":[96],"size":[97],"alone":[98],"does":[99],"not":[100],"resolve.BenchMAX":[101],"serves":[102],"as":[103],"evaluation":[107],"platform,":[108],"providing":[109],"promising":[111],"test":[112],"bed":[113],"promote":[115],"development":[117],"models.The":[121],"dataset":[122],"1":[123],"2":[126],"are":[127],"publicly":[128],"accessible.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}