{"id":"https://openalex.org/W7160429423","doi":"https://doi.org/10.1145/3805712.3809631","title":"Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation","display_name":"Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7160429423","doi":"https://doi.org/10.1145/3805712.3809631"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809631","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809631","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809631","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135452574","display_name":"Peiyang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiyang Liu","raw_affiliation_strings":["National Engineering Research Center for Software Engineering, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3658-9147","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Software Engineering, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135479300","display_name":"Qiang Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210106409","display_name":"China Institute of Finance and Capital Markets","ror":"https://ror.org/01mp98161","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210106409"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Yan","raw_affiliation_strings":["PX Securities, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-5006-3697","affiliations":[{"raw_affiliation_string":"PX Securities, Beijing, China","institution_ids":["https://openalex.org/I4210106409"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135439830","display_name":"Ziqiang Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ziqiang Cui","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-1742-7866","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135429273","display_name":"Di Liang","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":"Di Liang","raw_affiliation_strings":["Tencent Technology, Beijing, USA"],"raw_orcid":"https://orcid.org/0000-0002-3684-4550","affiliations":[{"raw_affiliation_string":"Tencent Technology, Beijing, USA","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135489168","display_name":"Xi Wang","orcid":"https://orcid.org/0000-0002-7572-6354"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Wang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-2316-8320","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135518819","display_name":"Wei Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Ye","raw_affiliation_strings":["National Engineering Research Center for Software Engineering, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9331-4716","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Software Engineering, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1232","last_page":"1243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.6297000050544739,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.6297000050544739,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.09359999746084213,"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":0.04729999974370003,"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/correctness","display_name":"Correctness","score":0.6672999858856201},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6604999899864197},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.5551000237464905},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5432000160217285},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5260999798774719},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.47620001435279846},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.46000000834465027},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.40869998931884766}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7131999731063843},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6672999858856201},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6604999899864197},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.5551000237464905},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5432000160217285},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5260999798774719},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.462799996137619},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.46000000834465027},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44690001010894775},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34540000557899475},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.2924000024795532},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C37381756","wikidata":"https://www.wikidata.org/wiki/Q20203288","display_name":"Representativeness heuristic","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.2624000012874603},{"id":"https://openalex.org/C2781466463","wikidata":"https://www.wikidata.org/wiki/Q621695","display_name":"Blame","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3805712.3809631","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809631","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2605.01302","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.01302","pdf_url":"https://arxiv.org/pdf/2605.01302","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809631","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809631","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7934902310371399}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Standard":[0],"Retrieval-Augmented":[1],"Generation":[2],"(RAG)":[3],"systems":[4],"predominantly":[5],"rely":[6],"on":[7,134],"semantic":[8],"relevance":[9,42],"as":[10,32],"a":[11,53,73,91,106],"proxy":[12],"for":[13,71],"utility.":[14],"However,":[15],"this":[16,63],"assumption":[17],"collapses":[18],"in":[19,86,148],"realistic":[20],"decision-making":[21,135],"scenarios":[22],"where":[23],"user":[24,97],"queries":[25],"are":[26],"laden":[27],"with":[28,78],"cognitive":[29],"biases,":[30],"such":[31,39],"false":[33],"premises":[34],"or":[35],"confirmation":[36],"bias.":[37],"In":[38],"cases,":[40],"maximizing":[41],"paradoxically":[43],"promotes":[44],"the":[45,58,124],"retrieval":[46,77],"of":[47],"sycophantic":[48],"evidence":[49],"that":[50,75,117,138],"reinforces":[51],"hallucinations,":[52],"critical":[54],"failure":[55],"we":[56,65,89],"term":[57],"\"Relevance-Robustness":[59],"Gap\".":[60],"To":[61],"bridge":[62],"gap,":[64],"propose":[66],"CoRM-RAG":[67,139],"(Counterfactual":[68],"Risk":[69],"Minimization":[70],"RAG),":[72],"framework":[74],"aligns":[76],"decision":[79],"safety":[80],"rather":[81],"than":[82],"mere":[83],"similarity.":[84],"Grounded":[85],"causal":[87],"intervention,":[88],"introduce":[90],"Cognitive":[92],"Perturbation":[93],"Protocol":[94],"to":[95,114,122],"simulate":[96],"biases":[98],"during":[99],"training,":[100],"which":[101],"is":[102,162],"then":[103],"distilled":[104],"into":[105],"lightweight":[107],"Evidence":[108],"Critic.":[109],"This":[110],"scoring":[111],"module":[112],"learns":[113],"identify":[115],"documents":[116],"possess":[118],"sufficient":[119],"evidential":[120],"strength":[121],"steer":[123],"model":[125],"toward":[126],"correctness":[127],"despite":[128],"adversarial":[129,149],"query":[130],"perturbations.":[131],"Extensive":[132],"experiments":[133],"benchmarks":[136],"demonstrate":[137],"significantly":[140],"outperforms":[141],"strong":[142],"dense":[143],"retrievers":[144],"and":[145],"LLM-based":[146],"rerankers":[147],"settings,":[150],"while":[151],"enabling":[152],"effective":[153],"risk-aware":[154],"abstention":[155],"through":[156],"reliable":[157],"robustness":[158],"scoring.":[159],"Our":[160],"code":[161],"available":[163],"at":[164],"https://github.com/PeiYangLiu/CoRM-RAG.git.":[165]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-07T00:00:00"}