{"id":"https://openalex.org/W4416034954","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.637","title":"Time to Revisit Exact Match","display_name":"Time to Revisit Exact Match","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034954","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.637"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.637","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.637","pdf_url":"https://aclanthology.org/2025.findings-emnlp.637.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.637.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066190395","display_name":"Auss Abbood","orcid":"https://orcid.org/0000-0002-4428-168X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Auss Abbood","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073342482","display_name":"Zaiqiao Meng","orcid":"https://orcid.org/0000-0001-5374-0318"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zaiqiao Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073413742","display_name":"Nigel Collier","orcid":"https://orcid.org/0000-0002-7230-4164"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nigel Collier","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":0.17070966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11903","last_page":"11926"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7444999814033508,"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/T10028","display_name":"Topic Modeling","score":0.7444999814033508,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.08380000293254852,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.03310000151395798,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6195999979972839},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5307999849319458},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.521399974822998},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.504800021648407},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4207000136375427},{"id":"https://openalex.org/keywords/mean-absolute-error","display_name":"Mean absolute error","score":0.41040000319480896},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4027000069618225},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.39899998903274536}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6195999979972839},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5807999968528748},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5307999849319458},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.521399974822998},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.504800021648407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46880000829696655},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C188154048","wikidata":"https://www.wikidata.org/wiki/Q6803609","display_name":"Mean absolute error","level":3,"score":0.41040000319480896},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4027000069618225},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3637999892234802},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3553999960422516},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29899999499320984},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2809000015258789},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27469998598098755},{"id":"https://openalex.org/C2779265950","wikidata":"https://www.wikidata.org/wiki/Q22906137","display_name":"Absolute scale","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2662999927997589},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.637","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.637","pdf_url":"https://aclanthology.org/2025.findings-emnlp.637.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: EMNLP 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:363217","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/50574.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.637","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.637","pdf_url":"https://aclanthology.org/2025.findings-emnlp.637.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6513702697","display_name":"CAM Doctoral Training Partnership","funder_award_id":"ES/Y001788/1","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"}],"funders":[{"id":"https://openalex.org/F4320334630","display_name":"Economic and Social Research Council","ror":"https://ror.org/03n0ht308"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034954.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Temporal":[0],"question":[1,50],"answering":[2,51],"is":[3,177],"an":[4],"established":[5],"method":[6],"for":[7,202,205],"evaluating":[8],"temporal":[9,49,81,162,206],"reasoning":[10],"in":[11,158],"large":[12,41],"language":[13],"models.":[14],"Expected":[15],"answers":[16],"are":[17,27,116],"often":[18],"numeric":[19],"(e.g.,":[20],"dates":[21],"or":[22],"durations),":[23],"yet":[24],"model":[25,151],"responses":[26],"evaluated":[28],"like":[29],"regular":[30],"text":[31],"with":[32,119,147,168],"exact":[33],"match":[34],"(EM),":[35],"unable":[36],"to":[37,57,85,154,178],"distinguish":[38],"small":[39],"from":[40,69,183],"errors.":[42,195],"In":[43],"this":[44],"investigative":[45],"work,":[46],"we":[47,109],"frame":[48],"as":[52],"a":[53,66,79],"numerical":[54],"estimation":[55],"task":[56],"assess":[58],"the":[59,92,140,143,172,184,200],"shortcomings":[60],"of":[61,71,142,161],"EM.":[62,89,136],"We":[63,90],"introduce":[64],"TempAnswerQA,":[65],"benchmark":[67],"distilled":[68],"Test":[70],"Time":[72],"and":[73,101,114,128,188],"TempTabQA,":[74],"where":[75],"all":[76],"questions":[77],"require":[78],"numerical,":[80],"answer,":[82],"allowing":[83],"us":[84],"evaluate":[86],"models":[87,130],"beyond":[88],"use":[91],"forecasting":[93],"metrics":[94,204],"symmetric":[95],"mean":[96,102],"absolute":[97,103],"percentage":[98],"error":[99,105,112,176],"(sMAPE)":[100],"scaled":[104],"(MASE).":[106],"With":[107],"sMAPE,":[108],"find":[110],"that":[111],"size":[113],"EM":[115,121],"decoupled.":[117],"Models":[118],"low":[120,124],"still":[122],"have":[123,131],"sMAPE":[125,133,187],"(both":[126],"20%),":[127],"some":[129],"high":[132,135],"despite":[134],"Scaling":[137],"errors":[138],"by":[139,180],"deviation":[141],"ground":[144,185],"truth":[145],"data":[146],"MASE":[148],"reshuff":[149],"les":[150],"rankings":[152],"compared":[153],"EM,":[155,191],"revealing":[156],"gaps":[157],"models\u2019":[159,173],"understanding":[160],"domain":[163],"knowledge,":[164],"especially":[165],"when":[166],"trained":[167],"synthetic":[169],"data.":[170],"Lastly,":[171],"most":[174],"frequent":[175],"deviate":[179],"only":[181],"\u00b11":[182],"truth.":[186],"MASE,":[189],"unlike":[190],"adequately":[192],"weight":[193],"these":[194],"Our":[196],"findings":[197],"1":[198],"underscore":[199],"need":[201],"specialised":[203],"QA":[207],"tasks.":[208]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-11-08T00:00:00"}