{"id":"https://openalex.org/W4416034884","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.550","title":"XL-Suite: Cross-Lingual Synthetic Training and Evaluation Data for Open-Ended Generation","display_name":"XL-Suite: Cross-Lingual Synthetic Training and Evaluation Data for Open-Ended Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034884","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.550"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.550","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.550","pdf_url":"https://aclanthology.org/2025.findings-emnlp.550.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.550.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073712726","display_name":"Vivek Iyer","orcid":"https://orcid.org/0000-0001-6441-9319"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vivek Iyer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023609587","display_name":"Pinzhen Chen","orcid":"https://orcid.org/0000-0003-0089-5118"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pinzhen Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039347839","display_name":"Ricardo Rei","orcid":"https://orcid.org/0000-0001-8265-1939"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ricardo Rei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038456766","display_name":"Alexandra Birch","orcid":"https://orcid.org/0000-0002-9022-3405"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandra Birch","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.15758763,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10418","last_page":"10432"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2962999939918518,"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":0.2962999939918518,"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":0.26969999074935913,"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/T12031","display_name":"Speech and dialogue systems","score":0.05270000174641609,"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/training","display_name":"Training (meteorology)","score":0.4629000127315521},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.2655999958515167},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.2574999928474426},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.24060000479221344},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.23690000176429749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5457000136375427},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4629000127315521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38499999046325684},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.24060000479221344},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.23690000176429749},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.23499999940395355},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.23250000178813934},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.22949999570846558}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.550","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.550","pdf_url":"https://aclanthology.org/2025.findings-emnlp.550.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"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/e8d7fdcf-5f56-4426-a247-76eeb0c6cb9f","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/e8d7fdcf-5f56-4426-a247-76eeb0c6cb9f","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Iyer, V, Chen, P, Rei, R & Birch, A 2025, XL-Suite : Cross-lingual synthetic training and evaluation data for open-ended generation. in Findings of the Association for Computational Linguistics : EMNLP 2025. pp. 10418\u201310432, 30th Conference on Empirical Methods in Natural Language Processing, Suzhou, China, 4/11/25. https://doi.org/10.18653/v1/2025.findings-emnlp.550","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/e8d7fdcf-5f56-4426-a247-76eeb0c6cb9f","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/e8d7fdcf-5f56-4426-a247-76eeb0c6cb9f","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Iyer, V, Chen, P, Rei, R & Birch, A 2025, XL-Suite : Cross-lingual synthetic training and evaluation data for open-ended generation. in Findings of the Association for Computational Linguistics : EMNLP 2025. pp. 10418\u201310432, 30th Conference on Empirical Methods in Natural Language Processing, Suzhou, China, 4/11/25. https://doi.org/10.18653/v1/2025.findings-emnlp.550","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.qub.ac.uk/portal:openaire/be56cf4d-961a-48ca-9511-b543f77f2a4a","is_oa":true,"landing_page_url":"https://pure.qub.ac.uk/en/publications/be56cf4d-961a-48ca-9511-b543f77f2a4a","pdf_url":null,"source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"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":"Iyer, V, Chen, P, Rei, R & Birch, A 2025, XL-Suite: cross-lingual synthetic training and evaluation data for open-ended generation. in C Christodoulopoulos, T Chakraborty, C Rose & V Peng (eds), Findings of the Association for Computational Linguistics: EMNLP 2025. Association for Computational Linguistics, Suzhou, China, pp. 10418-10432. https://doi.org/10.18653/v1/2025.findings-emnlp.550","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.550","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.550","pdf_url":"https://aclanthology.org/2025.findings-emnlp.550.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":[{"id":"https://openalex.org/F4320314707","display_name":"Government of the United Kingdom","ror":"https://ror.org/05wnh3t63"},{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034884.pdf","grobid_xml":"https://content.openalex.org/works/W4416034884.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Cross-lingual":[0],"open-ended":[1,126],"generationresponding":[2],"in":[3,104,124],"a":[4,20,31,114],"language":[5,41],"different":[6],"from":[7,66],"that":[8,46],"of":[9,39,102,107,116],"the":[10,61,99,105],"query-is":[11],"an":[12],"important":[13],"yet":[14],"understudied":[15],"problem.This":[16],"work":[17],"proposes":[18],"XL-Instruct,":[19],"novel":[21],"technique":[22],"for":[23,34],"generating":[24],"high-quality":[25],"synthetic":[26],"data.We":[27],"also":[28],"introduce":[29],"XL-AlpacaEval,":[30],"new":[32],"benchmark":[33],"evaluating":[35],"cross-lingual":[36,125],"generation":[37],"capabilities":[38],"large":[40],"models":[42],"(LLMs).Our":[43],"experiments":[44],"show":[45],"fine-tuning":[47],"with":[48],"just":[49],"8K":[50],"instructions":[51],"generated":[52],"using":[53],"our":[54,93],"XL-Instruct":[55,81,103],"significantly":[56],"improves":[57],"model":[58],"performance:":[59],"increasing":[60],"win":[62],"rate":[63],"against":[64],"GPT-4o-mini":[65],"7.4%":[67],"to":[68,86,121],"21.5%":[69],"and":[70,118],"improving":[71],"on":[72,80,92],"several":[73],"fine-grained":[74],"quality":[75],"metrics.Moreover,":[76],"base":[77],"LLMs":[78],"fine-tuned":[79],"exhibit":[82],"strong":[83],"zero-shot":[84],"improvements":[85],"same-language":[87],"question":[88],"answering,":[89],"as":[90],"shown":[91],"machine-translated":[94],"m-AlpacaEval.These":[95],"consistent":[96],"gains":[97],"highlight":[98],"promising":[100],"role":[101],"post-training":[106],"multilingual":[108],"LLMs.Finally,":[109],"we":[110],"publicly":[111],"release":[112],"XL-Suite,":[113],"collection":[115],"training":[117],"evaluation":[119],"data":[120],"facilitate":[122],"research":[123],"generation.":[127]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}