{"id":"https://openalex.org/W7166796572","doi":"https://doi.org/10.18653/v1/2026.findings-acl.667","title":"BOLT: Benchmarking Open-World Learning for Text Classification","display_name":"BOLT: Benchmarking Open-World Learning for Text Classification","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166796572","doi":"https://doi.org/10.18653/v1/2026.findings-acl.667"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.667","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.667","pdf_url":"https://aclanthology.org/2026.findings-acl.667.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.667.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139841422","display_name":"Chuan Qin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuan Qin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139778115","display_name":"Xi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xi Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139797770","display_name":"Jinpeng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinpeng Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139779856","display_name":"Hengshu Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hengshu Zhu","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":0.78612086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13624","last_page":"13658"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.737500011920929,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.737500011920929,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.031300000846385956,"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":0.01940000057220459,"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/benchmarking","display_name":"Benchmarking","score":0.567799985408783},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3384999930858612},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.2567000091075897},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.25459998846054077},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.25450000166893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6744999885559082},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.567799985408783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5347999930381775},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39879998564720154},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3264000117778778},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28439998626708984},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.667","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.667","pdf_url":"https://aclanthology.org/2026.findings-acl.667.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.667","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.667","pdf_url":"https://aclanthology.org/2026.findings-acl.667.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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5908771753311157}],"awards":[{"id":"https://openalex.org/G138355835","display_name":null,"funder_award_id":"62506352","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166796572.pdf","grobid_xml":"https://content.openalex.org/works/W7166796572.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text":[0,83,89],"classification":[1],"has":[2,34],"long":[3],"been":[4,16],"a":[5,38,73,144],"cornerstone":[6],"of":[7,64,191],"NLP,":[8],"yet":[9],"most":[10,162],"prior":[11,184],"work":[12],"and":[13,45,76,104,115,131,139,154,170,206,216],"benchmarks":[14,49],"have":[15],"limited":[17],"to":[18,26,95,111,166,172,174],"closed-world":[19],"settings,":[20],"where":[21],"all":[22],"classes":[23],"are":[24,218],"assumed":[25],"be":[27],"known":[28,114,155],"in":[29,210],"advance.In":[30],"contrast,":[31],"open-world":[32,195],"learning":[33],"recently":[35],"emerged":[36],"as":[37,61],"critical":[39],"paradigm":[40],"for":[41,82,137,141,150,194],"building":[42],"more":[43],"robust":[44],"realistic":[46],"systems.However,":[47],"existing":[48],"largely":[50],"focus":[51],"on":[52],"out-of-distribution":[53],"(OOD)":[54],"detection,":[55],"while":[56,100],"overlooking":[57],"broader":[58],"challenges":[59],"such":[60],"the":[62,189],"discovery":[63],"novel":[65,116],"categories.To":[66],"address":[67],"this":[68,211],"gap,":[69],"we":[70,187],"introduce":[71],"BOLT,":[72],"unified":[74],"Benchmark":[75],"evaluation":[77,200],"toolkit":[78],"supporting":[79],"Open-world":[80],"Learning":[81],"classification.BOLTencompasses":[84],"two":[85],"representative":[86],"tasks:":[87],"Open-set":[88],"Classification":[90],"(OSTC),":[91],"which":[92,109],"requires":[93],"models":[94],"classify":[96],"in-distribution":[97],"(ID)":[98],"samples":[99],"rejecting":[101],"OOD":[102],"inputs,":[103],"Generalized":[105],"Category":[106],"Discovery":[107],"(GCD),":[108],"aims":[110],"identify":[112],"both":[113],"categories":[117],"from":[118],"partially":[119],"labeled":[120,152],"corpora.We":[121],"carefully":[122],"curate":[123],"12":[124],"publicly":[125],"available":[126,219],"datasets":[127],"spanning":[128],"diverse":[129],"domains":[130],"benchmark":[132],"22":[133],"methods,":[134],"including":[135],"15":[136],"OSTC":[138],"7":[140],"GCD,":[142],"under":[143],"standardized":[145,199],"protocol":[146],"that":[147,202],"explicitly":[148],"accounts":[149],"varying":[151],"ratios":[153],"class":[156],"ratios.Our":[157],"results":[158],"reveal":[159],"key":[160],"challenges:":[161],"current":[163],"methods":[164],"tend":[165],"overfit":[167],"training":[168],"distributions":[169],"struggle":[171],"generalize":[173],"unseen":[175],"classes.Moreover,":[176],"by":[177],"comparing":[178],"our":[179],"lightweight":[180],"LLMbased":[181],"variants":[182],"with":[183],"open-set":[185],"baselines,":[186,215],"demonstrate":[188],"promise":[190],"leveraging":[192],"LLMs":[193],"text":[196],"classification.BOLT":[197],"provides":[198],"protocols":[201],"enable":[203],"fair":[204],"comparison":[205],"support":[207],"future":[208],"research":[209],"emerging":[212],"area.All":[213],"datasets,":[214],"tools":[217],"at":[220],"https:":[221],"//github.com/CNIC-DSL/BOLT.":[222]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}