{"id":"https://openalex.org/W7214927100","doi":"https://doi.org/10.18653/2026.uncertainlp-main.20","title":"Reliable but Design-Sensitive: Instrument Uncertainty in LLM Annotation","display_name":"Reliable but Design-Sensitive: Instrument Uncertainty in LLM Annotation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7214927100","doi":"https://doi.org/10.18653/2026.uncertainlp-main.20"},"language":"en","primary_location":{"id":"doi:10.18653/2026.uncertainlp-main.20","doi":"https://doi.org/10.18653/2026.uncertainlp-main.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.uncertainlp-main.20","pdf_url":"https://aclanthology.org/2026.uncertainlp-main.20.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Proceedings of the Third Workshop on Uncertainty-Aware NLP","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.uncertainlp-main.20.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153564586","display_name":"Thomas Reiter","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Reiter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113463465","display_name":"Christoph Kern","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Kern","raw_affiliation_strings":["Ludwig Maximilian University of Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwig Maximilian University of Munich , Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153630230","display_name":"Fedor Miasnikov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fedor Miasnikov","raw_affiliation_strings":["Ludwig Maximilian University of Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwig Maximilian University of Munich , Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139346102","display_name":"Sofiia Nikolenko","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sofiia Nikolenko","raw_affiliation_strings":["Ludwig Maximilian University of Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwig Maximilian University of Munich , Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078399314","display_name":"Robert Chew","orcid":"https://orcid.org/0000-0002-6979-1766","observed_orcids":["https://orcid.org/0000-0002-6979-1766","https://orcid.org/0000-0001-9875-2371"]},"institutions":[{"id":"https://openalex.org/I180297670","display_name":"RTI International","ror":"https://ror.org/052tfza37","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I137902535","https://openalex.org/I170897317","https://openalex.org/I180297670"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rob Chew","raw_affiliation_strings":["RTI International , North Carolina , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RTI International , North Carolina , USA","institution_ids":["https://openalex.org/I180297670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085081313","display_name":"Stephanie Eckman","orcid":"https://orcid.org/0000-0002-8577-4085","observed_orcids":["https://orcid.org/0000-0002-8577-4085"]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephanie Eckman","raw_affiliation_strings":["University of Maryland , Social Data Science Center , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland , Social Data Science Center , USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038390320","display_name":"Frauke Kreuter","orcid":"https://orcid.org/0000-0002-7339-2645","observed_orcids":["https://orcid.org/0000-0002-7339-2645"]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Frauke Kreuter","raw_affiliation_strings":["Ludwig Maximilian University of Munich , Germany","University of Maryland , Social Data Science Center , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwig Maximilian University of Munich , Germany","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"University of Maryland , Social Data Science Center , USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.65420338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"312","last_page":"327"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9761000275611877,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9761000275611877,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.010900000110268593,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.003700000001117587,"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/instrument-uncertainty","display_name":"instrument uncertainty","score":0.7979999780654907},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8640000224113464},{"id":"https://openalex.org/keywords/llm-annotation","display_name":"LLM annotation","score":0.6899999976158142},{"id":"https://openalex.org/keywords/offensive-language","display_name":"offensive language","score":0.6890000104904175},{"id":"https://openalex.org/keywords/hate-speech","display_name":"hate speech","score":0.9380000233650208},{"id":"https://openalex.org/keywords/prevalence-estimation","display_name":"prevalence estimation","score":0.8019999861717224},{"id":"https://openalex.org/keywords/confidence-scores","display_name":"confidence scores","score":0.9340000152587891},{"id":"https://openalex.org/keywords/human-annotation-comparison","display_name":"human annotation comparison","score":0.5149999856948853},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.40299999713897705},{"id":"https://openalex.org/keywords/social-media-text","display_name":"social media text","score":0.5370000004768372}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7639999985694885},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6700000166893005},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6491000056266785},{"id":"https://openalex.org/C176856949","wikidata":"https://www.wikidata.org/wiki/Q2001676","display_name":"Offensive","level":2,"score":0.6190000176429749},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5159000158309937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5146999955177307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5092999935150146},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4738999903202057},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.45890000462532043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42910000681877136},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.40700000524520874},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3763999938964844},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.34549999237060547},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2782999873161316}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.uncertainlp-main.20","doi":"https://doi.org/10.18653/2026.uncertainlp-main.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.uncertainlp-main.20","pdf_url":"https://aclanthology.org/2026.uncertainlp-main.20.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Proceedings of the Third Workshop on Uncertainty-Aware NLP","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2609.35824","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35824","pdf_url":"https://arxiv.org/pdf/2609.35824","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.2609.35824","doi":"https://doi.org/10.48550/arxiv.2609.35824","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.35824","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"}],"best_oa_location":{"id":"doi:10.18653/2026.uncertainlp-main.20","doi":"https://doi.org/10.18653/2026.uncertainlp-main.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.uncertainlp-main.20","pdf_url":"https://aclanthology.org/2026.uncertainlp-main.20.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Proceedings of the Third Workshop on Uncertainty-Aware NLP","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214927100.pdf","grobid_xml":"https://content.openalex.org/works/W7214927100.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W4387799916","https://openalex.org/W4402359543","https://openalex.org/W4416183472","https://openalex.org/W4417080482","https://openalex.org/W7152991919","https://openalex.org/W7155067999","https://openalex.org/W7167697156"],"related_works":["https://openalex.org/W7154898398","https://openalex.org/W7131792540","https://openalex.org/W7220698693","https://openalex.org/W7134282935","https://openalex.org/W7204802369","https://openalex.org/W7124951617","https://openalex.org/W7164510325","https://openalex.org/W7118873881","https://openalex.org/W7147548178","https://openalex.org/W7155067999"],"abstract_inverted_index":{"Large":[0],"language":[1,37,87],"models":[2],"(LLMs)":[3],"can":[4,160],"give":[5],"reliable":[6],"labels":[7,14],"under":[8],"one":[9,138,169],"setup":[10,170],"yet":[11],"change":[12],"those":[13],"when":[15,56],"researchers":[16],"make":[17],"other":[18],"reasonable":[19,166],"design":[20,46,61,71,154],"choices.We":[21],"tested":[22],"seven":[23],"LLMs,":[24],"12":[25],"task":[26,45,60,100,153,167],"designs,":[27],"three":[28],"independent":[29],"runs,":[30],"and":[31,38,44,72,88,133,155],"3,000":[32],"tweets":[33,65,136],"labeled":[34],"for":[35,62,85,90],"offensive":[36,86],"hate":[39,91],"speech.Repeating":[40],"the":[41,59,63,76,149],"same":[42,64],"model":[43,73,124,156],"produced":[47],"high":[48],"agreement":[49,129],"(median":[50,66],"Fleiss'":[51],"\u03ba":[52,68],"=":[53,69],"0.91).Agreement":[54],"fell":[55],"we":[57],"changed":[58],"Cohen's":[67],"0.76).Task":[70],"choice":[74,157],"increased":[75],"variance":[77,96],"of":[78,83],"estimated":[79],"prevalence":[80],"by":[81,144,152,164],"factors":[82],"76.7":[84],"110.6":[89],"speech":[92],"compared":[93,106],"with":[94,107,130],"sampling":[95],"alone.Variation":[97],"across":[98,111],"LLM":[99],"designs":[101],"reached":[102],"560-572":[103],"basis":[104,109,146],"points,":[105],"270-331":[108],"points":[110],"five":[112],"human":[113,131],"instrument":[114,158],"versions.Confidence":[115],"scores":[116,175],"did":[117],"not":[118],"solve":[119],"this":[120],"problem.They":[121],"tracked":[122],"repeated":[123],"outputs":[125],"more":[126],"closely":[127],"than":[128],"labels,":[132],"grouping":[134],"six":[135],"in":[137],"prompt":[139],"lowered":[140],"mean":[141],"offensive-language":[142],"confidence":[143,174],"660":[145],"points.We":[147],"call":[148],"variation":[150],"caused":[151],"uncertainty.Researchers":[159],"measure":[161],"it":[162],"only":[163],"comparing":[165],"designs.Repeating":[168],"or":[171],"relying":[172],"on":[173],"cannot":[176],"replace":[177],"that":[178],"test.":[179],"1":[180]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-01T00:00:00"}