{"id":"https://openalex.org/W4416595455","doi":"https://doi.org/10.63317/4zrfhra4azck","title":"MUCH: A Multilingual Claim Hallucination Benchmark","display_name":"MUCH: A Multilingual Claim Hallucination Benchmark","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W4416595455","doi":"https://doi.org/10.63317/4zrfhra4azck"},"language":null,"primary_location":{"id":"doi:10.63317/4zrfhra4azck","is_oa":false,"landing_page_url":"https://doi.org/10.63317/4zrfhra4azck","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.17081","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099054966","display_name":"J\u00e9r\u00e9mie Dentan","orcid":"https://orcid.org/0009-0001-5561-8030"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J\u00e9r\u00e9mie Dentan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Alexi Stanislas Canesse","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexi Stanislas Canesse","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051885442","display_name":"Davide Buscaldi","orcid":"https://orcid.org/0000-0003-1112-3789"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Davide Buscaldi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052180718","display_name":"Aymen Shabou","orcid":"https://orcid.org/0000-0001-8933-7053"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aymen Shabou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5031988385","display_name":"Sonia Haddad-Vanier","orcid":"https://orcid.org/0000-0001-6390-8882"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sonia Vanier","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02834403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2249","last_page":"2267"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.44620001316070557,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.44620001316070557,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.14589999616146088,"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/T14347","display_name":"Big Data and Digital Economy","score":0.11169999837875366,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8185999989509583},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.6032999753952026},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5619000196456909},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.516700029373169},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5055000185966492},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.46869999170303345},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.3009999990463257}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8185999989509583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7448999881744385},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6032999753952026},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5619000196456909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5590999722480774},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.516700029373169},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5055000185966492},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.46869999170303345},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42899999022483826},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.357699990272522},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27250000834465027},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.2590999901294708}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.63317/4zrfhra4azck","is_oa":false,"landing_page_url":"https://doi.org/10.63317/4zrfhra4azck","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.17081","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.17081","pdf_url":"https://arxiv.org/pdf/2511.17081","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,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.17081","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.17081","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.17081","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.17081","pdf_url":"https://arxiv.org/pdf/2511.17081","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,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Claim-level":[0],"Uncertainty":[1],"Quantification":[2],"(UQ)":[3],"is":[4],"a":[5,93],"promising":[6],"approach":[7,115],"to":[8,81],"mitigate":[9],"the":[10,22,69,107],"lack":[11],"of":[12,33,71,98,106,120],"reliability":[13],"in":[14,79,146],"Large":[15],"Language":[16],"Models":[17],"(LLMs).":[18],"We":[19],"introduce":[20],"MUCH,":[21],"first":[23],"claim-level":[24,59],"UQ":[25,127],"benchmark":[26],"designed":[27],"for":[28,117,144],"fair":[29],"and":[30,50,52,149],"reproducible":[31],"evaluation":[32],"future":[34,72],"methods":[35,74,128,139],"under":[36,129],"realistic":[37,130],"conditions.":[38],"It":[39],"includes":[40],"4,873":[41],"samples":[42],"across":[43],"four":[44,53],"European":[45],"languages":[46],"(English,":[47],"French,":[48],"Spanish,":[49],"German)":[51],"instruction-tuned":[54],"open-weight":[55],"LLMs.":[56],"Unlike":[57],"prior":[58],"benchmarks,":[60],"we":[61,91],"release":[62],"24":[63],"generation":[64,109],"logits":[65],"per":[66],"token,":[67],"facilitating":[68],"development":[70],"white-box":[73],"without":[75],"re-generating":[76],"data.":[77],"Moreover,":[78],"contrast":[80],"previous":[82],"benchmarks":[83],"that":[84,124,137],"rely":[85],"on":[86],"manual":[87],"or":[88],"LLM-based":[89],"segmentation,":[90],"propose":[92],"new":[94],"deterministic":[95],"algorithm":[96],"capable":[97],"segmenting":[99],"claims":[100],"using":[101],"as":[102,104],"little":[103],"0.2%":[105],"LLM":[108,121],"time.":[110],"This":[111],"makes":[112],"our":[113,134],"segmentation":[114],"suitable":[116],"real-time":[118],"monitoring":[119],"outputs,":[122],"ensuring":[123],"MUCH":[125],"evaluates":[126],"deployment":[131],"constraints.":[132],"Finally,":[133],"evaluations":[135],"show":[136],"current":[138],"still":[140],"have":[141],"substantial":[142],"room":[143],"improvement":[145],"both":[147],"performance":[148],"efficiency.":[150]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-11-25T00:00:00"}