{"id":"https://openalex.org/W4416035352","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1671","title":"SUE: Sparsity-based Uncertainty Estimation via Sparse Dictionary Learning","display_name":"SUE: Sparsity-based Uncertainty Estimation via Sparse Dictionary Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035352","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1671"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1671","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1671","pdf_url":"https://aclanthology.org/2025.emnlp-main.1671.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1671.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023796609","display_name":"Tam\u00e1s Ficsor","orcid":"https://orcid.org/0000-0002-8442-6652"},"institutions":[{"id":"https://openalex.org/I227486990","display_name":"University of Szeged","ror":"https://ror.org/01pnej532","country_code":"HU","type":"education","lineage":["https://openalex.org/I227486990"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Tam\u00e1s Ficsor","raw_affiliation_strings":["University of Szeged , Hungary"],"affiliations":[{"raw_affiliation_string":"University of Szeged , Hungary","institution_ids":["https://openalex.org/I227486990"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020987552","display_name":"G\u00e1bor Berend","orcid":"https://orcid.org/0000-0002-3845-4978"},"institutions":[{"id":"https://openalex.org/I227486990","display_name":"University of Szeged","ror":"https://ror.org/01pnej532","country_code":"HU","type":"education","lineage":["https://openalex.org/I227486990"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"G\u00e1bor Berend","raw_affiliation_strings":["University of Szeged , Hungary"],"affiliations":[{"raw_affiliation_string":"University of Szeged , Hungary","institution_ids":["https://openalex.org/I227486990"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5023796609"],"corresponding_institution_ids":["https://openalex.org/I227486990"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18382708,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"32900","last_page":"32917"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.43050000071525574,"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":0.43050000071525574,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.07479999959468842,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.06129999831318855,"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/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35440000891685486},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3352000117301941},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3206000030040741},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.3172999918460846},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.2913999855518341},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.2847000062465668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5752000212669373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5360000133514404},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35440000891685486},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3352000117301941},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2964000105857849},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27250000834465027},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27149999141693115},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2558000087738037},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1671","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1671","pdf_url":"https://aclanthology.org/2025.emnlp-main.1671.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1671","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1671","pdf_url":"https://aclanthology.org/2025.emnlp-main.1671.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035352.pdf","grobid_xml":"https://content.openalex.org/works/W4416035352.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"growing":[1],"deployment":[2],"of":[3,45,116,154],"deep":[4],"learning":[5,80],"models":[6],"in":[7,24,54,165],"real-world":[8],"applications":[9],"necessitates":[10],"not":[11],"only":[12],"high":[13,173],"predictive":[14,38,102],"accuracy,":[15],"but":[16],"also":[17],"mechanism":[18],"to":[19,94],"identify":[20],"unreliable":[21],"predictions,":[22],"especially":[23],"high-stakes":[25],"scenarios":[26],"where":[27],"decision":[28],"risk":[29],"must":[30],"be":[31],"minimized.Existing":[32],"methods":[33],"estimate":[34],"uncertainty":[35,72,164],"by":[36,81],"leveraging":[37],"confidence":[39],"(e.g.,":[40,48,57],"Softmax":[41],"Response),":[42],"structural":[43],"characteristics":[44],"representation":[46],"space":[47],"Mahalanobis":[49,127],"distance),":[50],"or":[51,150],"stochastic":[52],"variation":[53],"model":[55,171],"outputs":[56],"Bayesian":[58],"inference":[59],"techniques":[60],"such":[61],"as":[62],"Monte":[63],"Carlo":[64],"Dropout).In":[65],"this":[66],"work,":[67],"we":[68],"propose":[69],"a":[70],"novel":[71],"estimation":[73],"(UE)":[74],"framework":[75],"based":[76],"on":[77,131],"sparse":[78,99],"dictionary":[79,83],"identifying":[82],"atoms":[84],"associated":[85],"with":[86],"misclassified":[87],"samples.We":[88],"leverage":[89],"pointwise":[90],"mutual":[91],"information":[92],"(PMI)":[93],"quantify":[95],"the":[96,117,123,152,166,170],"association":[97],"between":[98],"features":[100],"and":[101,136,139,145],"failure.Our":[103],"method":[104],"-Sparsity-based":[105],"Uncertainty":[106],"Estimation":[107],"(SUE)is":[108],"computationally":[109],"efficient,":[110],"offers":[111],"interpretability":[112],"via":[113],"atom-level":[114],"analysis":[115,141],"dictionary,":[118],"has":[119],"no":[120],"assumption":[121],"about":[122],"class":[124],"distribution":[125],"(unlike":[126],"distance).We":[128],"evaluated":[129],"SUE":[130,148],"several":[132],"NLU":[133],"benchmarks":[134,142],"(GLUE":[135],"ANLI":[137],"tasks)":[138],"sentiment":[140],"(Twitter,":[143],"ParaDetox,":[144],"Jigsaw).In":[146],"general,":[147],"outperforms":[149],"matches":[151],"performance":[153],"other":[155],"methods.SUE":[156],"performs":[157],"particularly":[158],"well":[159],"when":[160,169],"there":[161],"is":[162],"considerable":[163],"model,":[167],"i.e.,":[168],"lacks":[172],"precision.":[174]},"counts_by_year":[],"updated_date":"2026-03-10T14:07:55.174380","created_date":"2025-11-08T00:00:00"}