{"id":"https://openalex.org/W7129015434","doi":"https://doi.org/10.1145/3773966.3778015","title":"Unsupervised Dense Retrieval with Conterfactual Contrastive Learning","display_name":"Unsupervised Dense Retrieval with Conterfactual Contrastive Learning","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129015434","doi":"https://doi.org/10.1145/3773966.3778015"},"language":null,"primary_location":{"id":"doi:10.1145/3773966.3778015","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3778015","pdf_url":null,"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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3773966.3778015","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Haitian Chen","orcid":"https://orcid.org/0009-0006-7208-9675"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitian Chen","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China and Quan Cheng Laboratory, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-7208-9675","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China and Quan Cheng Laboratory, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126125146","display_name":"Qingyao Ai","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyao Ai","raw_affiliation_strings":["Quan Cheng Laboratory, Beijing, China and Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5030-709X","affiliations":[{"raw_affiliation_string":"Quan Cheng Laboratory, Beijing, China and Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yujia Zhou","orcid":"https://orcid.org/0000-0002-3530-3787"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujia Zhou","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3530-3787","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiao Wang","orcid":"https://orcid.org/0000-0002-5151-2773"},"institutions":[{"id":"https://openalex.org/I146563203","display_name":"University of International Business and Economics","ror":"https://ror.org/05khqpb71","country_code":"CN","type":"education","lineage":["https://openalex.org/I146563203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Wang","raw_affiliation_strings":["University of International Business and Economics, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5151-2773","affiliations":[{"raw_affiliation_string":"University of International Business and Economics, Beijing, China","institution_ids":["https://openalex.org/I146563203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064349338","display_name":"YiquN Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqun Liu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0140-4512","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111565371","display_name":"Lin Fen","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fen Lin","raw_affiliation_strings":["WeChat Search Application Department, Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0008-8728-3475","affiliations":[{"raw_affiliation_string":"WeChat Search Application Department, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126103390","display_name":"Qin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Liu","raw_affiliation_strings":["WeChat Search Application Department, Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0003-7096-8527","affiliations":[{"raw_affiliation_string":"WeChat Search Application Department, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20597265,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"47","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.38119998574256897,"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":0.38119998574256897,"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":0.18709999322891235,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.12759999930858612,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.6945000290870667},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6351000070571899},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.43799999356269836},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3553999960422516},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.3244999945163727},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.31369999051094055},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3073999881744385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7343000173568726},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.6945000290870667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6834999918937683},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6351000070571899},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5719000101089478},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.43799999356269836},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3197999894618988},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C149189445","wikidata":"https://www.wikidata.org/wiki/Q5283894","display_name":"Divergence-from-randomness model","level":3,"score":0.2858000099658966},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2694000005722046},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3773966.3778015","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3778015","pdf_url":null,"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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3773966.3778015","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3778015","pdf_url":null,"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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4161643385887146}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2536015822","https://openalex.org/W2648699835","https://openalex.org/W2783640434","https://openalex.org/W2940927814","https://openalex.org/W2951434086","https://openalex.org/W2963341956","https://openalex.org/W2964012472","https://openalex.org/W2979826702","https://openalex.org/W3021397474","https://openalex.org/W3034654340","https://openalex.org/W3034912391","https://openalex.org/W3099700870","https://openalex.org/W3099884329","https://openalex.org/W3104564752","https://openalex.org/W3153624757","https://openalex.org/W3157758108","https://openalex.org/W3166968943","https://openalex.org/W3177934633","https://openalex.org/W4213088395","https://openalex.org/W4214585697","https://openalex.org/W4224330422","https://openalex.org/W4252076394","https://openalex.org/W4252222626","https://openalex.org/W4283796213","https://openalex.org/W4297834088","https://openalex.org/W4308644260","https://openalex.org/W4380303532","https://openalex.org/W4381827193","https://openalex.org/W4384659456","https://openalex.org/W4387846590"],"related_works":[],"abstract_inverted_index":{"Efficiently":[0],"retrieving":[1],"a":[2,8,14,119,151,157,176,197],"concise":[3],"set":[4],"of":[5,52,70,78,150,164,179],"candidates":[6],"from":[7],"large":[9],"doc-":[10,94],"ument":[11],"corpus":[12],"remains":[13],"pivotal":[15],"challenge":[16],"in":[17,86,113],"Information":[18],"Retrieval":[19],"(IR).":[20],"Neural":[21],"retrieval":[22,26,72,121,166,260],"models,":[23,34],"particularly":[24],"dense":[25,71,120,259],"models":[27,73,261],"built":[28],"with":[29,127,190],"transformers":[30],"and":[31,54,159,171,187,238],"pretrained":[32],"language":[33],"have":[35,45,103],"been":[36,47,104],"popular":[37],"due":[38],"to":[39,56,61,66,101,123,129,133,146,156,228,234],"their":[40,50,76,99,139],"superior":[41],"performance.":[42],"However,":[43],"criticisms":[44],"also":[46,142],"raised":[48],"on":[49,184,223,251],"lack":[51],"explainability":[53,163],"vulnerability":[55],"adversarial":[57,266],"attacks.":[58],"In":[59],"response":[60],"these":[62,224],"challenges,":[63],"we":[64,174,194,214],"propose":[65,175,215],"improve":[67,161,235],"the":[68,162,165,206,230,236,252,257,269],"robustness":[69,237,264],"by":[74,169],"enhancing":[75],"sensitivity":[77,85,117],"fine-grained":[79],"relevance":[80,100,254],"signals.":[81],"A":[82],"model":[83,122],"achieving":[84],"this":[87],"context":[88],"should":[89],"exhibit":[90,262],"high":[91],"variances":[92,109],"when":[93],"uments'":[95],"key":[96,207,247],"passages":[97,208,248],"determining":[98],"queries":[102],"modified,":[105],"while":[106],"maintaining":[107],"low":[108],"for":[110],"other":[111],"changes":[112],"irrelevant":[114],"passages.":[115,192],"This":[116],"allows":[118],"produce":[124],"robust":[125],"results":[126],"respect":[128],"attacks":[130],"that":[131,209],"try":[132],"promote":[134],"documents":[135],"without":[136,249],"actually":[137,154],"increasing":[138],"relevance.":[140,212],"It":[141],"makes":[143],"it":[144],"possible":[145],"analyze":[147],"which":[148],"part":[149],"document":[152],"is":[153],"relevant":[155],"query,":[158],"thus":[160],"model.":[167],"Motivated":[168],"causality":[170],"counterfactual":[172,180,191,201,225],"analysis,":[173],"se-":[177],"ries":[178],"regularization":[181],"methods":[182],"based":[183,222],"game":[185,199],"theory":[186],"unsupervised":[188],"learning":[189,220,232],"Specifically,":[193],"first":[195],"introduce":[196],"cooperative":[198],"theory-based":[200],"passage":[202],"extraction":[203],"method,":[204],"identifying":[205],"can":[210,245],"influence":[211],"Then":[213],"several":[216],"subsequent":[217],"unsuper-":[218],"vised":[219],"tasks,":[221],"passages,":[226],"serve":[227],"regularize":[229],"model's":[231],"process":[233],"sensitivity.":[239],"Experiments":[240],"show":[241],"that,":[242],"our":[243],"method":[244],"extract":[246],"reliance":[250],"passage-level":[253],"annotations.":[255],"Moreover,":[256],"regularized":[258],"heightened":[263],"against":[265],"attacks,":[267],"surpassing":[268],"state-of-the-art":[270],"anti-attack":[271],"methods.":[272]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-17T00:00:00"}