{"id":"https://openalex.org/W7166854411","doi":"https://doi.org/10.18653/v1/2026.findings-acl.500","title":"GALA: Geometric Data Selection with Strategic Prospecting for Large Language Model Self-training","display_name":"GALA: Geometric Data Selection with Strategic Prospecting for Large Language Model Self-training","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166854411","doi":"https://doi.org/10.18653/v1/2026.findings-acl.500"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.500","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.500","pdf_url":"https://aclanthology.org/2026.findings-acl.500.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: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.500.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139778618","display_name":"Zhongwei Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongwei Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139779020","display_name":"Ruihao Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruihao Liao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125664590","display_name":"Zimo Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zimo Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139806789","display_name":"Chong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139851959","display_name":"Xian-Sheng Hua","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xian-Sheng Hua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139777408","display_name":"Xiao Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Luo","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":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84365358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10281","last_page":"10293"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.1289999932050705,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.1289999932050705,"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/T10028","display_name":"Topic Modeling","score":0.12229999899864197,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.08500000089406967,"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/prospecting","display_name":"Prospecting","score":0.597100019454956},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5565999746322632},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4007999897003174},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.38280001282691956},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.3179999887943268}],"concepts":[{"id":"https://openalex.org/C175181221","wikidata":"https://www.wikidata.org/wiki/Q1650350","display_name":"Prospecting","level":2,"score":0.597100019454956},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5565999746322632},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5426999926567078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41370001435279846},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4007999897003174},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.38280001282691956},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3521000146865845},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C104065381","wikidata":"https://www.wikidata.org/wiki/Q1002535","display_name":"Geometric modeling","level":2,"score":0.26269999146461487}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.500","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.500","pdf_url":"https://aclanthology.org/2026.findings-acl.500.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: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.500","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.500","pdf_url":"https://aclanthology.org/2026.findings-acl.500.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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166854411.pdf","grobid_xml":"https://content.openalex.org/works/W7166854411.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Self-training":[0],"has":[1],"emerged":[2],"as":[3],"a":[4,17,38,118],"promising":[5],"direction":[6],"for":[7,49,110],"autonomously":[8],"improving":[9],"large":[10],"language":[11],"models":[12],"(LLMs).Existing":[13],"approaches":[14],"typically":[15],"adopt":[16],"generate-and-filter":[18],"paradigm":[19],"based":[20,91],"on":[21,78,92,138],"rejection":[22],"sampling,":[23],"which":[24],"could":[25],"suffer":[26],"from":[27,63,88],"inefficiency":[28],"and":[29,60,66,82,108],"low-quality":[30],"reasoning":[31,112],"paths.Towards":[32],"this":[33,35],"end,":[34],"paper":[36],"proposes":[37],"novel":[39],"framework":[40],"named":[41],"Geometric":[42],"Data":[43],"Selection":[44],"with":[45],"Strategic":[46],"Prospecting":[47],"(GALA)":[48],"LLM":[50],"self-training.The":[51],"core":[52],"of":[53,127,134,144],"our":[54,72],"GALA":[55,74,147],"is":[56],"to":[57,96,123,129],"identify":[58],"diverse":[59],"informative":[61],"samples":[62],"redundant":[64],"data":[65,98],"exploit":[67,101],"them":[68],"more":[69],"strategically.In":[70],"particular,":[71],"proposed":[73,146],"first":[75],"conducts":[76],"clustering":[77],"latent":[79],"sentence":[80],"embeddings":[81],"then":[83],"selects":[84],"an":[85],"anchor":[86],"sample":[87],"each":[89],"cluster":[90],"the":[93,125,131,135,142,145],"geometric":[94],"distance":[95],"reduce":[97],"redundancy.To":[99],"further":[100],"these":[102],"samples,":[103],"we":[104,116],"conduct":[105],"strategic":[106],"brainstorming":[107],"reflection":[109],"high-quality":[111],"trajectory":[113],"prospecting.In":[114],"addition,":[115],"introduce":[117],"lightweight":[119],"dynamic":[120],"validation":[121],"module":[122],"validate":[124,141],"reliability":[126],"mini-batches":[128],"ensure":[130],"overall":[132],"quality":[133],"data.Extensive":[136],"experiments":[137],"various":[139],"benchmarks":[140],"effectiveness":[143],"against":[148],"several":[149],"competing":[150],"baselines.":[151]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}