{"id":"https://openalex.org/W7224829601","doi":"https://doi.org/10.48550/arxiv.2610.40278","title":"Neighborhood Elites: Quality-Diversity Search for Uncertainty Quantification in Question Answering","display_name":"Neighborhood Elites: Quality-Diversity Search for Uncertainty Quantification in Question Answering","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224829601","doi":"https://doi.org/10.48550/arxiv.2610.40278"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.40278","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.40278","pdf_url":"https://arxiv.org/pdf/2610.40278","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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.40278","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123205915","display_name":"Mesut Ceylan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ceylan, Mesut","raw_affiliation_strings":["ETH Zurich , Zurich , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich , Zurich , Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159941452","display_name":"Arda Baris Basaran","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Basaran, Arda Baris","raw_affiliation_strings":["ETH Zurich , Zurich , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich , Zurich , Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063968302","display_name":"Elgar Fleisch","orcid":"https://orcid.org/0000-0002-4842-1117","observed_orcids":["https://orcid.org/0000-0002-4842-1117"]},"institutions":[{"id":"https://openalex.org/I202963720","display_name":"University of St.Gallen","ror":"https://ror.org/0561a3s31","country_code":"CH","type":"education","lineage":["https://openalex.org/I202963720"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Fleisch, Elgar","raw_affiliation_strings":["ETH Zurich , Zurich , Switzerland","University of St.Gallen , St.Gallen , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich , Zurich , Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"University of St.Gallen , St.Gallen , Switzerland","institution_ids":["https://openalex.org/I202963720"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024270049","display_name":"Filipe Barata","orcid":"https://orcid.org/0000-0002-3905-2380","observed_orcids":["https://orcid.org/0000-0002-3905-2380"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Barata, Filipe","raw_affiliation_strings":["ETH Zurich , Zurich , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich , Zurich , Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.6904000043869019,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.6904000043869019,"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":0.2257000058889389,"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":0.025100000202655792,"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/uncertainty-quantification","display_name":"uncertainty quantification","score":0.8889999985694885},{"id":"https://openalex.org/keywords/question-answering","display_name":"question answering","score":0.9470000267028809},{"id":"https://openalex.org/keywords/input-disturbances","display_name":"input perturbation","score":0.8569999933242798},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7149999737739563},{"id":"https://openalex.org/keywords/fault-detection","display_name":"fault detection","score":0.7990000247955322},{"id":"https://openalex.org/keywords/paraphrasing","display_name":"paraphrase","score":0.5370000004768372},{"id":"https://openalex.org/keywords/extractive-question-answering","display_name":"extractive question answering","score":0.7620000243186951},{"id":"https://openalex.org/keywords/semantic-entropy","display_name":"semantic entropy","score":0.5490000247955322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7102000117301941},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6100999712944031},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.554099977016449},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5239999890327454},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.503000020980835},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4607999920845032},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.44040000438690186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43869999051094055},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.4352000057697296},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41830000281333923},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3321000039577484},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2930000126361847},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28999999165534973},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C177803969","wikidata":"https://www.wikidata.org/wiki/Q29205","display_name":"Uncertainty analysis","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C137209882","wikidata":"https://www.wikidata.org/wiki/Q1403517","display_name":"Measurement uncertainty","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2531000077724457},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.40278","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.40278","pdf_url":"https://arxiv.org/pdf/2610.40278","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.2610.40278","doi":"https://doi.org/10.48550/arxiv.2610.40278","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.40278","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.40278","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.40278","pdf_url":"https://arxiv.org/pdf/2610.40278","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224829601.pdf","grobid_xml":"https://content.openalex.org/works/W7224829601.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W758372786","https://openalex.org/W2557764419","https://openalex.org/W2799007037","https://openalex.org/W2963748441","https://openalex.org/W2963969878","https://openalex.org/W2968154628","https://openalex.org/W2988421999","https://openalex.org/W3021338988","https://openalex.org/W3177813494","https://openalex.org/W4327810158","https://openalex.org/W4376167329","https://openalex.org/W4388139328","https://openalex.org/W4399803256","https://openalex.org/W4402270921","https://openalex.org/W4409362870","https://openalex.org/W4411600576"],"related_works":["https://openalex.org/W4389116007","https://openalex.org/W7163882487","https://openalex.org/W7166856567","https://openalex.org/W7083001230","https://openalex.org/W4411119967","https://openalex.org/W6959801663","https://openalex.org/W7166843344","https://openalex.org/W6891360484","https://openalex.org/W4417325985","https://openalex.org/W6891942796"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4],"increasingly":[5],"capable,":[6],"yet":[7],"they":[8],"produce":[9],"wrong":[10],"answers":[11],"indistinguishable":[12],"from":[13,47,191],"correct":[14],"ones.":[15],"In":[16],"question":[17],"answering":[18],"(QA),":[19],"such":[20],"an":[21],"error":[22],"propagates":[23],"unnoticed":[24],"into":[25],"downstream":[26],"tasks.":[27],"Perturbation-based":[28],"uncertainty":[29,46,180],"quantification":[30],"(UQ)":[31],"addresses":[32],"this":[33,54,251],"by":[34,60,106,111,243],"probing":[35],"a":[36,39,130,140,148],"model":[37],"over":[38,227,240],"set":[40,55,103],"of":[41,80,101,160,165,215],"input":[42,137],"rewrites":[43,69,154],"and":[44,87,113,143,162,182,186,199,223,246,250],"reading":[45],"how":[48,88],"much":[49],"its":[50],"predictions":[51],"vary.":[52],"Yet":[53],"is":[56,82,97,104,126],"usually":[57],"built":[58,127],"generically,":[59],"free":[61],"paraphrasing,":[62],"token-level":[63],"perturbation,":[64],"or":[65],"adversarial":[66],"search.":[67],"Such":[68],"leave":[70],"two":[71,156],"things":[72],"uncontrolled":[73],"that":[74,118,151],"matter":[75],"in":[76,211],"QA:":[77],"what":[78],"kind":[79,159],"change":[81],"made":[83],"to":[84,121,128],"the":[85,90,93,99,102,107,114,158,163,176,192,216,228,255],"context,":[86],"explicitly":[89],"context":[91],"supports":[92],"answer.":[94],"When":[95],"neither":[96],"controlled,":[98],"composition":[100],"determined":[105],"generator":[108,119],"rather":[109],"than":[110,236],"design,":[112],"estimate":[115],"inherits":[116],"whatever":[117],"happens":[120],"produce.":[122],"Quality-diversity":[123],"(QD)":[124],"search":[125,183],"cover":[129],"predefined":[131],"exploration":[132],"space,":[133],"so":[134],"we":[135],"recast":[136],"perturbation":[138],"as":[139,254],"QD":[141],"problem":[142],"propose":[144],"\\emph{neighborhood":[145],"elites":[146],"(NE)},":[147],"neighborhood":[149,173,256],"constructor":[150,210],"spreads":[152],"answer-preserving":[153],"across":[155],"axes,":[157],"edit":[161],"explicitness":[164],"support.":[166],"We":[167],"compare":[168],"NE":[169,203,232],"against":[170,187,207],"three":[171,188],"other":[172,209],"constructors,":[174],"holding":[175],"editor,":[177],"QA":[178],"model,":[179],"measure":[181],"objective":[184],"fixed,":[185],"scores":[189],"read":[190],"original":[193],"context.":[194],"Across":[195],"five":[196,200],"extractive-QA":[197],"datasets":[198],"instruction-tuned":[201],"LLMs,":[202],"improves":[204],"failure":[205,234],"detection":[206],"every":[208],"at":[212],"least":[213],"24":[214],"25":[217],"dataset-model":[218],"pairs,":[219],"reaching":[220],"0.726":[221],"AUROC":[222,245],"0.211":[224],"AUPRC":[225,248],"lift":[226],"base":[229],"rate.":[230],"Additionally,":[231],"detects":[233],"better":[235],"semantic":[237],"entropy":[238],"computed":[239],"decoder":[241],"samples,":[242],"0.074":[244],"0.062":[247],"lift,":[249],"advantage":[252],"widens":[253],"grows.":[257]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-31T00:00:00"}