{"id":"https://openalex.org/W6941403045","doi":"https://doi.org/10.13140/rg.2.2.16233.67684","title":"The ICL Consistency Test","display_name":"The ICL Consistency Test","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W6941403045","doi":"https://doi.org/10.13140/rg.2.2.16233.67684"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2312.04945","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.04945","pdf_url":"https://arxiv.org/pdf/2312.04945","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2312.04945","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Weber, Lucas","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weber, Lucas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007465102","display_name":"Elia Bruni","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bruni, Elia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018069499","display_name":"Dieuwke Hupkes","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hupkes Dieuwke","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":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.051500000059604645,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.051500000059604645,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.0421999990940094,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.020899999886751175,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/consistency-testing","display_name":"consistency testing","score":0.49799999594688416}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.8519999980926514},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7728000283241272},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6481000185012817},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.598800003528595},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4675999879837036},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.4569000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42089998722076416},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40299999713897705},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39489999413490295},{"id":"https://openalex.org/C37279795","wikidata":"https://www.wikidata.org/wiki/Q2492305","display_name":"Consistency model","level":3,"score":0.3813000023365021},{"id":"https://openalex.org/C175652121","wikidata":"https://www.wikidata.org/wiki/Q4379351","display_name":"Causal consistency","level":5,"score":0.36880001425743103},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3100000023841858},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.28790000081062317},{"id":"https://openalex.org/C82029504","wikidata":"https://www.wikidata.org/wiki/Q4373882","display_name":"Sequential consistency","level":4,"score":0.287200003862381},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C31388003","wikidata":"https://www.wikidata.org/wiki/Q7624548","display_name":"Strong consistency","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26989999413490295},{"id":"https://openalex.org/C193429382","wikidata":"https://www.wikidata.org/wiki/Q232405","display_name":"Metric system","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2312.04945","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.04945","pdf_url":"https://arxiv.org/pdf/2312.04945","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2312.04945","doi":"https://doi.org/10.48550/arxiv.2312.04945","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2312.04945","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.13140/rg.2.2.16233.67684","doi":"https://doi.org/10.13140/rg.2.2.16233.67684","is_oa":false,"landing_page_url":"https://doi.org/10.13140/rg.2.2.16233.67684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2312.04945","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.04945","pdf_url":"https://arxiv.org/pdf/2312.04945","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6941403045.pdf","grobid_xml":"https://content.openalex.org/works/W6941403045.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4389521024","https://openalex.org/W4412889652","https://openalex.org/W4392271211","https://openalex.org/W4389520466","https://openalex.org/W4404781025","https://openalex.org/W7118002202","https://openalex.org/W7140108207","https://openalex.org/W4386043335","https://openalex.org/W4389518275","https://openalex.org/W7166807961"],"abstract_inverted_index":{"Just":[0],"like":[1,20],"the":[2,49,57,78],"previous":[3],"generation":[4],"of":[5,34,43,122,143],"task-tuned":[6],"models,":[7,146],"large":[8],"language":[9,89],"models":[10],"(LLMs)":[11],"that":[12,103],"are":[13],"adapted":[14],"to":[15,56,118,133],"tasks":[16],"via":[17],"prompt-based":[18,37],"methods":[19],"in-context-learning":[21],"(ICL)":[22],"perform":[23],"well":[24],"in":[25,30,36],"some":[26],"setups":[27,75],"but":[28],"not":[29],"others.":[31],"This":[32],"lack":[33,42,156],"consistency":[35,51,106,149],"learning":[38],"hints":[39],"at":[40],"a":[41,54,68,101,115,123],"robust":[44,157],"generalisation.":[45,158],"We":[46,92,138],"here":[47],"introduce":[48],"ICL":[50],"test":[52,82],"--":[53,63],"contribution":[55],"GenBench":[58],"collaborative":[59],"benchmark":[60],"task":[61],"(CBT)":[62],"which":[64],"evaluates":[65],"how":[66,152],"consistent":[67],"model":[69,105,136],"makes":[70],"predictions":[71,126],"across":[72,107],"many":[73],"different":[74,86,98],"while":[76],"using":[77],"same":[79],"data.":[80],"The":[81,110],"is":[83,112],"based":[84],"on":[85,114,129],"established":[87],"natural":[88],"inference":[90],"tasks.":[91],"provide":[93],"preprocessed":[94],"data":[95],"constituting":[96],"96":[97],"'setups'":[99],"and":[100,128,147],"metric":[102,111,150],"estimates":[104],"these":[108],"setups.":[109],"provided":[113],"fine-grained":[116],"level":[117,132],"understand":[119],"what":[120],"properties":[121],"setup":[124],"render":[125],"unstable":[127],"an":[130,140],"aggregated":[131],"compare":[134],"overall":[135],"consistency.":[137],"conduct":[139],"empirical":[141],"analysis":[142],"eight":[144],"state-of-the-art":[145],"our":[148],"reveals":[151],"all":[153],"tested":[154],"LLMs":[155]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2025-10-10T00:00:00"}