{"id":"https://openalex.org/W7204079324","doi":"https://doi.org/10.48550/arxiv.2608.20853","title":"MGAL: A Multilingual Granularity-Aware Long-Context Benchmark","display_name":"MGAL: A Multilingual Granularity-Aware Long-Context Benchmark","publication_year":2026,"publication_date":"2026-08-21","ids":{"openalex":"https://openalex.org/W7204079324","doi":"https://doi.org/10.48550/arxiv.2608.20853"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.20853","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20853","pdf_url":"https://arxiv.org/pdf/2608.20853","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.20853","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129470102","display_name":"Chunhan Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chunhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103210439","display_name":"Chenglin Xu","orcid":"https://orcid.org/0000-0002-1584-6282","observed_orcids":["https://orcid.org/0000-0002-1584-6282"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Chenglin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016368463","display_name":"Zongyang Zhang","orcid":"https://orcid.org/0000-0003-1358-4933","observed_orcids":["https://orcid.org/0000-0003-1358-4933"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zongyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148021364","display_name":"Jiale Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jiale","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147952788","display_name":"Zhuoxi Rao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rao, Zhuoxi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021123104","display_name":"Xudong Jia","orcid":"https://orcid.org/0000-0001-7911-8869","observed_orcids":["https://orcid.org/0000-0001-7911-8869"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Xudong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147956160","display_name":"Junxiu He","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Junxiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135315775","display_name":"Menglin Yang","orcid":"https://orcid.org/0000-0003-2510-5282","observed_orcids":["https://orcid.org/0000-0003-2510-5282"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Menglin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008124931","display_name":"Wenjuan Gong","orcid":"https://orcid.org/0000-0001-7805-3629","observed_orcids":["https://orcid.org/0000-0001-7805-3629","https://orcid.org/0000-0003-1239-6332"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gong, Wenjuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065674830","display_name":"Zhengzhe Liu","orcid":"https://orcid.org/0000-0002-8434-3224","observed_orcids":["https://orcid.org/0000-0002-8434-3224"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhengzhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084658659","display_name":"Chengwei Qin","orcid":"https://orcid.org/0000-0002-1121-2100","observed_orcids":["https://orcid.org/0000-0002-1121-2100"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Chengwei","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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9369999766349792,"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":0.9369999766349792,"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":0.054999999701976776,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.004399999976158142,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/multilingual-benchmark","display_name":"multilingual benchmark","score":0.652999997138977},{"id":"https://openalex.org/keywords/united-nations-report","display_name":"United Nations report","score":0.7680000066757202},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.7979999780654907},{"id":"https://openalex.org/keywords/discourse-roles","display_name":"discourse roles","score":0.3959999978542328},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6449999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7509999871253967},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.7433000206947327},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.7264999747276306},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6338000297546387},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6158000230789185},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.597000002861023},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5888000130653381},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5210999846458435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5023999810218811},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4327000081539154},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4124000072479248},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2962000072002411},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29100000858306885},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C120012220","wikidata":"https://www.wikidata.org/wiki/Q1754533","display_name":"Source text","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.20853","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20853","pdf_url":"https://arxiv.org/pdf/2608.20853","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.20853","doi":"https://doi.org/10.48550/arxiv.2608.20853","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.20853","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.20853","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20853","pdf_url":"https://arxiv.org/pdf/2608.20853","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320328618","display_name":"Lingnan University","ror":"https://ror.org/0563pg902"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204079324.pdf","grobid_xml":"https://content.openalex.org/works/W7204079324.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W3021338988","https://openalex.org/W3034870693","https://openalex.org/W4327810158","https://openalex.org/W4382603041","https://openalex.org/W4386555476","https://openalex.org/W4387355352","https://openalex.org/W4388979610","https://openalex.org/W4389519019","https://openalex.org/W4391709268","https://openalex.org/W4391876619","https://openalex.org/W4394778349","https://openalex.org/W4401043020","https://openalex.org/W4402671766","https://openalex.org/W4403749280","https://openalex.org/W4411119262","https://openalex.org/W4411630029","https://openalex.org/W4412889578","https://openalex.org/W4415337897","https://openalex.org/W7133239970"],"related_works":["https://openalex.org/W4417090457","https://openalex.org/W4386272986","https://openalex.org/W7140129605","https://openalex.org/W7118840579","https://openalex.org/W4404781182","https://openalex.org/W4415337897","https://openalex.org/W4415959329","https://openalex.org/W4388093359","https://openalex.org/W4402671258","https://openalex.org/W4391709268"],"abstract_inverted_index":{"Evaluation":[0],"of":[1,71,106,181,232],"long-context":[2,45,108],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"has":[7],"advanced":[8],"rapidly.":[9],"However,":[10],"most":[11],"existing":[12],"benchmarks":[13],"are":[14],"limited":[15],"to":[16,57,165],"the":[17,39,61,87,96,178,182,211],"document":[18,88,97],"level":[19],"and":[20,43,77,79,91,98,116,133,161,190,196,230],"focus":[21],"mainly":[22],"on":[23,227],"high-resource":[24],"languages,":[25],"leaving":[26],"many":[27],"fine-grained":[28],"challenges":[29],"insufficiently":[30],"evaluated.":[31],"To":[32],"address":[33],"this":[34],"gap,":[35],"we":[36,118,216],"present":[37],"MGAL,":[38],"first":[40],"multilingual,":[41],"granularity-":[42],"position-aware":[44],"benchmark.":[46],"MGAL":[47],"is":[48],"constructed":[49],"from":[50,210],"United":[51],"Nations":[52],"(UN)":[53],"reports":[54],"spanning":[55],"8K":[56],"128K":[58],"tokens":[59],"across":[60,110],"six":[62],"official":[63],"UN":[64],"languages.":[65,144],"It":[66],"covers":[67],"four":[68],"coherent":[69],"levels":[70],"linguistic":[72],"granularity":[73],"(word,":[74],"sentence,":[75],"paragraph,":[76],"document)":[78],"further":[80,146],"stratifies":[81],"entries":[82],"by":[83],"their":[84],"position":[85],"within":[86],"(begin,":[89],"middle,":[90],"end),":[92],"indexed":[93],"at":[94,125],"both":[95],"paragraph":[99],"levels.":[100],"This":[101],"design":[102],"enables":[103],"systematic":[104],"diagnosis":[105],"multilingual":[107],"comprehension":[109],"different":[111],"granularities.":[112],"Through":[113],"extensive":[114],"experiments":[115],"analyses,":[117],"find":[119],"that:":[120],"(1)":[121,151],"LLMs":[122],"perform":[123],"well":[124],"word-level":[126],"tasks":[127],"but":[128,208],"struggle":[129],"with":[130,222],"coarser-grained":[131],"ones;":[132],"(2)":[134,191],"Closed-source":[135],"models":[136,163,202],"retain":[137],"a":[138],"clear":[139],"performance":[140],"advantage":[141],"in":[142,184,198,220],"lower-resource":[143],"We":[145],"identify":[147],"two":[148],"new":[149],"challenges:":[150],"Under":[152],"local":[153],"semantic":[154],"crowding,":[155],"where":[156,201],"neighboring":[157],"sentences":[158],"share":[159],"topics":[160],"entities,":[162],"tend":[164],"follow":[166],"surface":[167],"cues":[168],"(e.g.,":[169,187],"connectives":[170],"like":[171],"``however''":[172],"or":[173],"repeated":[174],"entities)":[175],"rather":[176],"than":[177],"discourse":[179],"role":[180],"sentence":[183],"surrounding":[185],"context":[186],"background,":[188],"outcome);":[189],"A":[192],"gap":[193],"between":[194],"fluency":[195],"consistency":[197],"generated":[199],"outputs,":[200],"produce":[203],"text":[204],"that":[205],"reads":[206],"smoothly":[207],"drifts":[209],"source":[212],"facts.":[213],"In":[214],"addition,":[215],"observe":[217],"several":[218],"patterns":[219],"line":[221],"prior":[223],"studies,":[224],"including":[225],"reliance":[226],"nearby":[228],"evidence":[229],"reuse":[231],"options":[233],"under":[234],"uncertainty.":[235]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-25T00:00:00"}