{"id":"https://openalex.org/W4412673559","doi":"https://doi.org/10.1145/3731120.3744578","title":"W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question Answering","display_name":"W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question Answering","publication_year":2025,"publication_date":"2025-07-18","ids":{"openalex":"https://openalex.org/W4412673559","doi":"https://doi.org/10.1145/3731120.3744578"},"language":"en","primary_location":{"id":"doi:10.1145/3731120.3744578","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731120.3744578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114494476","display_name":"Jinming Nian","orcid":"https://orcid.org/0009-0007-4240-5777"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinming Nian","raw_affiliation_strings":["Santa Clara University, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0009-0007-4240-5777","affiliations":[{"raw_affiliation_string":"Santa Clara University, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075223216","display_name":"Zhiyuan Peng","orcid":"https://orcid.org/0000-0002-9870-4422"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyuan Peng","raw_affiliation_strings":["Santa Clara University, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9870-4422","affiliations":[{"raw_affiliation_string":"Santa Clara University, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101774659","display_name":"Qifan Wang","orcid":"https://orcid.org/0000-0002-7570-5756"},"institutions":[{"id":"https://openalex.org/I3197470489","display_name":"Alpha Omega Alpha Medical Honor Society","ror":"https://ror.org/057q9nn35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3197470489"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qifan Wang","raw_affiliation_strings":["Meta AI, Menlo Park, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7570-5756","affiliations":[{"raw_affiliation_string":"Meta AI, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I3197470489","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101972978","display_name":"Yi Fang","orcid":"https://orcid.org/0000-0001-6572-4315"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Fang","raw_affiliation_strings":["Santa Clara University, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6572-4315","affiliations":[{"raw_affiliation_string":"Santa Clara University, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.0309,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.98886196,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"136","last_page":"146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":0.998199999332428,"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":0.9914000034332275,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6866220831871033},{"id":"https://openalex.org/keywords/open-domain","display_name":"Open domain","score":0.6727584600448608},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6528756022453308},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5153734087944031},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41574713587760925},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3537006676197052},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16953271627426147}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6866220831871033},{"id":"https://openalex.org/C2993776861","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Open domain","level":3,"score":0.6727584600448608},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6528756022453308},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5153734087944031},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41574713587760925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3537006676197052},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16953271627426147},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731120.3744578","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731120.3744578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1979263599","https://openalex.org/W2065240770","https://openalex.org/W2101105183","https://openalex.org/W2912924812","https://openalex.org/W2963341956","https://openalex.org/W2963748441","https://openalex.org/W3021397474","https://openalex.org/W3027879771","https://openalex.org/W3099700870","https://openalex.org/W3100107515","https://openalex.org/W3154670582","https://openalex.org/W3217305727","https://openalex.org/W4205807230","https://openalex.org/W4252076394","https://openalex.org/W4320813768","https://openalex.org/W4327810158","https://openalex.org/W4385569963","https://openalex.org/W4385570798","https://openalex.org/W4385571271","https://openalex.org/W4385573057","https://openalex.org/W4387561528","https://openalex.org/W4387561549","https://openalex.org/W4389518895","https://openalex.org/W4389519118","https://openalex.org/W4389520468","https://openalex.org/W4389520486","https://openalex.org/W4389523718","https://openalex.org/W4391376033","https://openalex.org/W4392963986","https://openalex.org/W4394700684","https://openalex.org/W4398795713","https://openalex.org/W4399317490","https://openalex.org/W4399836941","https://openalex.org/W4399837475","https://openalex.org/W4400525811","https://openalex.org/W4401042773","https://openalex.org/W4401043313","https://openalex.org/W4401044046","https://openalex.org/W4401306979","https://openalex.org/W4402671977","https://openalex.org/W4404634776","https://openalex.org/W4406840883"],"related_works":["https://openalex.org/W2391533720","https://openalex.org/W2951097643","https://openalex.org/W4309395021","https://openalex.org/W3091989500","https://openalex.org/W4406245437","https://openalex.org/W3215363805","https://openalex.org/W204133468","https://openalex.org/W2991310128","https://openalex.org/W4307481286","https://openalex.org/W2395174199"],"abstract_inverted_index":{"In":[0,77],"knowledge-intensive":[1],"tasks":[2],"such":[3],"as":[4,47,95,145],"open-domain":[5],"question":[6,135],"answering":[7],"(OpenQA),":[8],"large":[9],"language":[10],"models":[11,181],"(LLMs)":[12],"often":[13],"struggle":[14],"to":[15,62,70,104,162,174,180],"generate":[16,129],"factual":[17],"answers,":[18],"relying":[19],"solely":[20],"on":[21],"their":[22],"internal":[23],"(parametric)":[24],"knowledge.":[25],"To":[26],"address":[27],"this":[28,78],"limitation,":[29],"Retrieval-Augmented":[30],"Generation":[31],"(RAG)":[32],"systems":[33],"enhance":[34],"LLMs":[35],"by":[36,121],"retrieving":[37],"relevant":[38],"information":[39],"from":[40,90],"external":[41],"sources,":[42],"thereby":[43],"positioning":[44],"the":[45,63,71,91,102,110,115,123,126,130],"retriever":[46,103],"a":[48,83,134],"pivotal":[49],"component.":[50],"Although":[51],"dense":[52,150],"retrieval":[53,169],"demonstrates":[54],"state-of-the-art":[55],"performance,":[56],"its":[57],"training":[58,88],"poses":[59],"challenges":[60],"due":[61],"scarcity":[64],"of":[65,74,97],"ground-truth":[66],"evidence,":[67],"largely":[68],"attributed":[69],"high":[72],"costs":[73],"human":[75],"annotation.":[76],"paper,":[79],"we":[80,113],"propose":[81],"W-RAG,":[82],"method":[84],"that":[85,107,125,164],"draws":[86],"weak":[87],"signals":[89],"downstream":[92],"task":[93],"(such":[94],"OpenQA)":[96],"an":[98],"LLM,":[99],"and":[100,170],"fine-tunes":[101],"prioritize":[105],"passages":[106,117,141],"most":[108],"benefit":[109],"task.":[111],"Specifically,":[112],"rerank":[114],"top-k":[116],"retrieved":[118],"via":[119],"BM25":[120],"assessing":[122],"probability":[124],"LLM":[127],"will":[128],"correct":[131],"answer":[132],"for":[133,149],"given":[136],"each":[137],"passage.":[138],"The":[139],"highest-ranking":[140],"are":[142],"then":[143],"used":[144],"positive":[146],"fine-tuning":[147],"examples":[148],"retrieval.":[151],"We":[152],"conduct":[153],"comprehensive":[154],"experiments":[155],"across":[156],"four":[157],"publicly":[158],"available":[159],"OpenQA":[160,171],"datasets":[161],"demonstrate":[163],"our":[165],"approach":[166],"enhances":[167],"both":[168],"performance":[172],"compared":[173],"baseline":[175],"models,":[176],"achieving":[177],"results":[178],"comparable":[179],"fine-tuned":[182],"with":[183],"human-labeled":[184],"data.":[185],"Source":[186],"code":[187],"is":[188],"published.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}