{"id":"https://openalex.org/W4416034640","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.612","title":"Evaluating Large Language Models for Cross-Lingual Retrieval","display_name":"Evaluating Large Language Models for Cross-Lingual Retrieval","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034640","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.612"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.612","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.612","pdf_url":"https://aclanthology.org/2025.findings-emnlp.612.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.612.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111271041","display_name":"Longfei Zuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Longfei Zuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017474543","display_name":"P. C. Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pingjun Hong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114367840","display_name":"Oliver Kraus","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oliver Kraus","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088832285","display_name":"Barbara Plank","orcid":"https://orcid.org/0000-0002-4394-1965"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Barbara Plank","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076365848","display_name":"Robert Litschko","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert Litschko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43282702,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11415","last_page":"11429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.4749000072479248,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.4749000072479248,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.12370000034570694,"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":0.05999999865889549,"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/language-model","display_name":"Language model","score":0.37959998846054077},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.34139999747276306},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.3160000145435333},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.28189998865127563},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.241799995303154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.677299976348877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49799999594688416},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49619999527931213},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.3160000145435333},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.262800008058548},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.241799995303154},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.23919999599456787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.612","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.612","pdf_url":"https://aclanthology.org/2025.findings-emnlp.612.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.612","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.612","pdf_url":"https://aclanthology.org/2025.findings-emnlp.612.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/W4416034640.pdf","grobid_xml":"https://content.openalex.org/works/W4416034640.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-stage":[0],"information":[1,191],"retrieval":[2,53,172,192,219,224,250],"(IR)":[3],"has":[4,193,225],"become":[5],"a":[6,26],"widely-adopted":[7],"paradigm":[8],"in":[9,136,155,190,211,248],"search.While":[10],"Large":[11],"Language":[12],"Models":[13],"(LLMs)":[14,189],"have":[15],"been":[16,226],"extensively":[17],"evaluated":[18],"as":[19,91],"second-stage":[20],"reranking":[21,103],"models":[22,188],"for":[23,33,58,161],"monolingual":[24,218],"IR,":[25],"systematic":[27],"large-scale":[28],"comparison":[29],"is":[30,62],"still":[31],"lacking":[32],"cross-lingual":[34,171,222],"IR":[35],"(CLIR).Moreover,":[36],"while":[37],"prior":[38,214,235],"work":[39,184,215],"shows":[40],"that":[41,82,95,107],"LLM-based":[42],"rerankers":[43,109,135,148],"improve":[44],"CLIR":[45,80,138,239],"performance,":[46],"their":[47,209],"evaluation":[48,75],"setup":[49],"relies":[50],"on":[51,76,111,217,237,241],"lexical":[52],"with":[54,88,101,116,139],"machine":[55],"translation":[56,99],"(MT)":[57],"the":[59,96,119,126,130,228,233,245,249],"first":[60,127],"stage.This":[61],"not":[63],"only":[64,234],"prohibitively":[65],"expensive":[66],"but":[67],"also":[68],"prone":[69],"to":[70,128,243],"error":[71],"propagation":[72],"across":[73],"stages.Our":[74],"passage-level":[77],"and":[78,94,134,220],"document-level":[79],"reveals":[81],"further":[83,105],"gains":[84,196],"can":[85],"be":[86],"achieved":[87],"multilingual":[89],"bi-encoders":[90],"first-stage":[92],"retrievers":[93,133],"benefits":[97],"of":[98,121,230],"diminishes":[100],"stronger":[102],"models.We":[104],"show":[106],"pairwise":[108],"based":[110],"instructiontuned":[112],"LLMs":[113],"perform":[114],"competitively":[115],"listwise":[117],"rerankers.To":[118],"best":[120,229],"our":[122,231],"knowledge,":[123,232],"we":[124],"are":[125],"study":[129],"interaction":[131],"between":[132],"two-stage":[137],"LLMs.Our":[140],"findings":[141],"reveal":[142],"that,":[143],"without":[144],"MT,":[145],"current":[146],"state-of-the-art":[147],"fall":[149],"severely":[150],"short":[151],"when":[152,173],"directly":[153],"applied":[154],"CLIR.*":[156],"Equal":[157],"contribution.unavailable":[158],"or":[159],"unreliable":[160],"many":[162],"low-resource":[163],"languages":[164],"(Haddow":[165],"et":[166,178,181,201,204,253],"al.,":[167,179,182,202,205,254],"2022),":[168],"adversely":[169],"affecting":[170],"translations":[174],"contain":[175],"errors":[176],"(Litschko":[177],"2022a;Guo":[180],"2024).Recent":[183],"leveraging":[185],"large":[186],"language":[187,246],"demonstrated":[194],"promising":[195],"over":[197],"baseline":[198],"systems":[199],"(Ma":[200],"2024(Ma":[203],",":[206],"2023)),":[207],"highlighting":[208],"capability":[210],"ranking":[212],"tasks.While":[213],"focuses":[216],"reranking,":[221],"LLMbased":[223,238],"understudied.To":[227],"works":[236],"rely":[240],"MT":[242],"bridge":[244],"gap":[247],"stage":[251],"(Adeyemi":[252],"2024a)":[255]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}