{"id":"https://openalex.org/W4416034331","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.849","title":"XRAG: Cross-lingual Retrieval-Augmented Generation","display_name":"XRAG: Cross-lingual Retrieval-Augmented Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034331","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.849"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.849","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.849","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.849","pdf_url":"https://aclanthology.org/2025.findings-emnlp.849.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2025.findings-emnlp.849.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062908102","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0003-2968-2888","observed_orcids":["https://orcid.org/0000-0003-2968-2888","https://orcid.org/0000-0003-2860-1783"]},"institutions":[{"id":"https://openalex.org/I71030271","display_name":"Heidelberg Institute for Theoretical Studies","ror":"https://ror.org/01f7bcy98","country_code":"DE","type":"facility","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414","https://openalex.org/I223822909","https://openalex.org/I71030271"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Heidelberg Institute for Theoretical Studies gGmbH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Heidelberg Institute for Theoretical Studies gGmbH","institution_ids":["https://openalex.org/I71030271"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080114729","display_name":"Sony Trenous","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sony Trenous","raw_affiliation_strings":["Amazon AGI","de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":[]},{"raw_affiliation_string":"de","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063685873","display_name":"Leonardo F. R. Ribeiro","orcid":"https://orcid.org/0000-0003-2639-942X","observed_orcids":["https://orcid.org/0000-0003-2639-942X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leonardo F. R. Ribeiro","raw_affiliation_strings":["Amazon AGI","de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":[]},{"raw_affiliation_string":"de","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070594684","display_name":"Bill Byrne","orcid":"https://orcid.org/0000-0003-1896-4492","observed_orcids":["https://orcid.org/0000-0003-1896-4492"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bill Byrne","raw_affiliation_strings":["Amazon AGI","de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":[]},{"raw_affiliation_string":"de","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022896682","display_name":"Felix Hieber","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felix Hieber","raw_affiliation_strings":["Amazon AGI","de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":[]},{"raw_affiliation_string":"de","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.3566,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.98711903,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"15669","last_page":"15690"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.951200008392334,"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":0.951200008392334,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.025299999862909317,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.010499999858438969,"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-information-retrieval","display_name":"multilingual information retrieval","score":0.8349999785423279},{"id":"https://openalex.org/keywords/monolingual-retrieval","display_name":"monolingual retrieval","score":0.921999990940094},{"id":"https://openalex.org/keywords/llm-reasoning","display_name":"LLM reasoning","score":0.6000000238418579},{"id":"https://openalex.org/keywords/news-articles","display_name":"news articles","score":0.718999981880188}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.76910001039505},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7193999886512756},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.694599986076355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.569100022315979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5353999733924866},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.4203000068664551},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3995000123977661},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2937999963760376},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.849","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.849","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.849","pdf_url":"https://aclanthology.org/2025.findings-emnlp.849.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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"},{"id":"pmh:oai:arXiv.org:2505.10089","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.10089","pdf_url":"https://arxiv.org/pdf/2505.10089","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.10089","doi":"https://doi.org/10.48550/arxiv.2505.10089","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.10089","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.849","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.849","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.849","pdf_url":"https://aclanthology.org/2025.findings-emnlp.849.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034331.pdf","grobid_xml":"https://content.openalex.org/works/W4416034331.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4402683011","https://openalex.org/W4404782057","https://openalex.org/W6979329113","https://openalex.org/W7171963735","https://openalex.org/W7220748447","https://openalex.org/W6948242698","https://openalex.org/W4403883362","https://openalex.org/W4415273199","https://openalex.org/W4413374917","https://openalex.org/W4414957389"],"abstract_inverted_index":{"We":[0],"propose":[1],"XRAG,":[2],"a":[3,89],"novel":[4,64],"benchmark":[5,91],"designed":[6],"to":[7,36,44],"evaluate":[8],"the":[9,21,27,48,78,100,118,132,136],"generation":[10,149],"abilities":[11],"of":[12,51,150],"LLMs":[13,107],"in":[14,69,113,117,131,140],"cross-lingual":[15,102,114],"Retrieval-Augmented":[16],"Generation":[17],"(RAG)":[18],"settings":[19],"where":[20],"user":[22],"language":[23,128],"does":[24],"not":[25],"match":[26],"retrieval":[28,120,134],"results.XRAG":[29],"is":[30],"constructed":[31],"from":[32],"recent":[33],"news":[34],"articles":[35],"ensure":[37],"that":[38,71],"its":[39],"questions":[40,70],"require":[41,72],"external":[42],"knowledge":[43],"be":[45],"answered.It":[46],"covers":[47],"real-world":[49],"scenarios":[50],"monolingual":[52,119],"and":[53,56,83],"multilingual":[54,133],"retrieval,":[55],"provides":[57],"relevancy":[58],"annotations":[59],"for":[60,92],"each":[61],"retrieved":[62,143],"document.Our":[63],"dataset":[65],"construction":[66],"pipeline":[67],"results":[68,104],"complex":[73],"reasoning,":[74],"as":[75,88],"evidenced":[76],"by":[77],"significant":[79],"gap":[80],"between":[81],"human":[82],"LLM":[84,94],"performance.Consequently,":[85],"XRAG":[86],"serves":[87],"valuable":[90],"studying":[93],"reasoning":[95,141],"abilities,":[96],"even":[97],"before":[98],"considering":[99],"additional":[101],"complexity.Experimental":[103],"on":[105],"five":[106],"uncover":[108],"two":[109],"previously":[110],"unreported":[111],"challenges":[112],"RAG:":[115],"1)":[116],"setting,":[121,135],"all":[122],"evaluated":[123],"models":[124],"struggle":[125],"with":[126],"response":[127],"correctness;":[129],"2)":[130],"main":[137],"challenge":[138],"lies":[139],"over":[142],"information":[144],"across":[145],"languages":[146],"rather":[147],"than":[148],"non-English":[151],"text.":[152],"1":[153]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2025-11-08T00:00:00"}