{"id":"https://openalex.org/W3196856979","doi":null,"title":"Exposing Length Divergence Bias of Textual Matching Models.","display_name":"Exposing Length Divergence Bias of Textual Matching Models.","publication_year":2021,"publication_date":"2021-09-06","ids":{"openalex":"https://openalex.org/W3196856979","mag":"3196856979"},"language":"en","primary_location":{"id":"mag:3196856979","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2109.02431","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.02431","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079795665","display_name":"Lan Jiang","orcid":"https://orcid.org/0000-0002-4735-3845","observed_orcids":["https://orcid.org/0000-0002-4735-3845"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lan Jiang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4735-3845","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073493925","display_name":"Tianshu Lyu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianshu Lyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100934884","display_name":"Chong Meng","orcid":"https://orcid.org/0009-0000-0981-4762","observed_orcids":["https://orcid.org/0009-0000-0981-4762"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong Meng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0000-0981-4762","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoyong Lyu","orcid":"https://orcid.org/0000-0003-3578-4848","observed_orcids":["https://orcid.org/0000-0003-3578-4848"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoyong Lyu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3578-4848","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5054482111","display_name":"Dawei Yin","orcid":"https://orcid.org/0000-0002-8846-2001","observed_orcids":["https://orcid.org/0000-0002-8846-2001","https://orcid.org/0000-0002-0684-6205"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dawei Yin","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8846-2001","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":false,"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":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.7836999893188477,"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":0.7836999893188477,"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":0.14560000598430634,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.00989999994635582,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/robustness","display_name":"robustness","score":0.6589999794960022},{"id":"https://openalex.org/keywords/adversarial-evaluation","display_name":"adversarial evaluation","score":0.7070000171661377},{"id":"https://openalex.org/keywords/adversarial-training","display_name":"adversarial training","score":0.8669999837875366},{"id":"https://openalex.org/keywords/label-bias","display_name":"label bias","score":0.628000020980835},{"id":"https://openalex.org/keywords/training-data-bias","display_name":"training data bias","score":0.6779999732971191},{"id":"https://openalex.org/keywords/probing-tasks","display_name":"probing tasks","score":0.5070000290870667},{"id":"https://openalex.org/keywords/out-of-distribution-generalization","display_name":"out-of-distribution generalization","score":0.7829999923706055},{"id":"https://openalex.org/keywords/dataset-bias","display_name":"data bias","score":0.3199999928474426}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7084690928459167},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6511985063552856},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6276010870933533},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6246157884597778},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4943575859069824},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.47805076837539673},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4680352509021759},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.45036008954048157},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4402560889720917},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4326513409614563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4164457321166992},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34482210874557495},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.272276371717453},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.23491206765174866},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3196856979","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2109.02431","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3196856979","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2109.02431","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W11155487","https://openalex.org/W1869587854","https://openalex.org/W2120735855","https://openalex.org/W2164456230","https://openalex.org/W2170245882","https://openalex.org/W2250539671","https://openalex.org/W2265289447","https://openalex.org/W2286300105","https://openalex.org/W2593833795","https://openalex.org/W2608787653","https://openalex.org/W2626778328","https://openalex.org/W2896457183","https://openalex.org/W2932893307","https://openalex.org/W2945802750","https://openalex.org/W2950235146","https://openalex.org/W2963310665","https://openalex.org/W2963508788","https://openalex.org/W2963615308","https://openalex.org/W2964121744","https://openalex.org/W3037888573","https://openalex.org/W3101033885","https://openalex.org/W4292353911"],"related_works":["https://openalex.org/W4285185565","https://openalex.org/W4385482202","https://openalex.org/W4382491060","https://openalex.org/W2738347542","https://openalex.org/W4392011709","https://openalex.org/W4408863477","https://openalex.org/W7127396740","https://openalex.org/W2940009958","https://openalex.org/W4225983788","https://openalex.org/W3153750116"],"abstract_inverted_index":{"Despite":[0],"the":[1,35,51,59,94,109,132,152,177,185],"remarkable":[2],"success":[3],"deep":[4],"models":[5,63,138,183],"have":[6],"achieved":[7],"in":[8,156],"Textual":[9],"Matching":[10],"(TM),":[11],"their":[12,147],"robustness":[13,178],"issue":[14,32],"is":[15,128],"still":[16],"a":[17,26,161],"topic":[18],"of":[19,39,54,61,78,182],"concern.":[20],"In":[21],"this":[22,31,45],"work,":[23],"we":[24,97,114,159,174],"propose":[25,160],"new":[27],"perspective":[28],"to":[29,64,145,150],"study":[30],"--":[33],"via":[34],"length":[36,82,141,153],"divergence":[37,83,154],"bias":[38,46,53,155],"TM":[40,56,62,72,95,157],"models.":[41],"We":[42,67],"conclude":[43],"that":[44,76,103,118,136,173],"stems":[47],"from":[48],"two":[49],"parts:":[50],"label":[52],"existing":[55],"datasets":[57],"and":[58,74,101,179],"sensitivity":[60],"superficial":[65],"information.":[66],"critically":[68],"examine":[69],"widely":[70],"used":[71],"datasets,":[73],"find":[75],"all":[77,104,121,137],"them":[79],"follow":[80],"specific":[81],"distributions":[84],"by":[85,123,131],"labels,":[86],"providing":[87],"direct":[88],"cues":[89],"for":[90,93],"predictions.":[91],"As":[92],"models,":[96,158],"conduct":[98],"adversarial":[99,111,163],"evaluation":[100],"show":[102],"models'":[105],"performances":[106],"drop":[107],"on":[108],"out-of-distribution":[110],"test":[112],"sets":[113],"construct,":[115],"which":[116],"demonstrates":[117],"they":[119],"are":[120],"misled":[122],"biased":[124],"training":[125,144,164,168],"sets.":[126],"This":[127],"also":[129],"confirmed":[130],"\\textit{SentLen}":[133],"probing":[134],"task":[135],"capture":[139],"rich":[140],"information":[142],"during":[143],"facilitate":[146],"performances.":[148],"Finally,":[149],"alleviate":[151],"practical":[162],"method":[165],"using":[166],"bias-free":[167],"data.":[169],"Our":[170],"experiments":[171],"indicate":[172],"successfully":[175],"improve":[176],"generalization":[180],"ability":[181],"at":[184],"same":[186],"time.":[187]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-09-13T00:00:00"}