{"id":"https://openalex.org/W4416016551","doi":"https://doi.org/10.1145/3746252.3761103","title":"Unbiased Reasoning for Knowledge-Intensive Tasks in Large Language Models via Conditional Front-Door Adjustment","display_name":"Unbiased Reasoning for Knowledge-Intensive Tasks in Large Language Models via Conditional Front-Door Adjustment","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416016551","doi":"https://doi.org/10.1145/3746252.3761103"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761103","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761103","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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746252.3761103","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108777422","display_name":"Bo Zhao","orcid":"https://orcid.org/0009-0007-3114-4452"},"institutions":[{"id":"https://openalex.org/I204823248","display_name":"Huazhong Agricultural University","ror":"https://ror.org/023b72294","country_code":"CN","type":"education","lineage":["https://openalex.org/I204823248"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Zhao","raw_affiliation_strings":["Huazhong Agricultural University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong Agricultural University, Wuhan, China","institution_ids":["https://openalex.org/I204823248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101638511","display_name":"Yinghao Zhang","orcid":"https://orcid.org/0000-0001-6084-3278"},"institutions":[{"id":"https://openalex.org/I204823248","display_name":"Huazhong Agricultural University","ror":"https://ror.org/023b72294","country_code":"CN","type":"education","lineage":["https://openalex.org/I204823248"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinghao Zhang","raw_affiliation_strings":["Huazhong Agricultural University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong Agricultural University, Wuhan, China","institution_ids":["https://openalex.org/I204823248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100743349","display_name":"Ziqi Xu","orcid":"https://orcid.org/0000-0003-1748-5801"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ziqi Xu","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039040673","display_name":"Yongli Ren","orcid":"https://orcid.org/0000-0002-3137-9653"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yongli Ren","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021983750","display_name":"Xiuzhen Zhang","orcid":"https://orcid.org/0000-0001-5558-3790"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiuzhen Zhang","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070730125","display_name":"Renqiang Luo","orcid":"https://orcid.org/0009-0002-8313-9835"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renqiang Luo","raw_affiliation_strings":["Jilin University, Changchun, China"],"affiliations":[{"raw_affiliation_string":"Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049033206","display_name":"Zaiwen Feng","orcid":"https://orcid.org/0000-0003-1618-3553"},"institutions":[{"id":"https://openalex.org/I204823248","display_name":"Huazhong Agricultural University","ror":"https://ror.org/023b72294","country_code":"CN","type":"education","lineage":["https://openalex.org/I204823248"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zaiwen Feng","raw_affiliation_strings":["Huazhong Agricultural University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong Agricultural University, Wuhan, China","institution_ids":["https://openalex.org/I204823248"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089615958","display_name":"Feng Xia","orcid":"https://orcid.org/0000-0002-8324-1859"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Feng Xia","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5108777422"],"corresponding_institution_ids":["https://openalex.org/I204823248"],"apc_list":null,"apc_paid":null,"fwci":7.0294,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.9687307,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4315","last_page":"4325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5913000106811523,"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":0.5913000106811523,"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":0.17669999599456787,"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":0.04639999940991402,"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":0.8149999976158142},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6001999974250793},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5113000273704529},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.4875999987125397},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4699999988079071},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.4514999985694885},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3508000075817108}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.8149999976158142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7135999798774719},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6001999974250793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5523999929428101},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5113000273704529},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.4875999987125397},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4699999988079071},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.4514999985694885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4487999975681305},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.3260999917984009},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29170000553131104},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2671999931335449}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3761103","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761103","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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746252.3761103","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761103","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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2889787757","https://openalex.org/W2963123047","https://openalex.org/W2963866616","https://openalex.org/W3177323791","https://openalex.org/W3190126809","https://openalex.org/W4280518705","https://openalex.org/W4310494058","https://openalex.org/W4313304293","https://openalex.org/W4322766882","https://openalex.org/W4364384032","https://openalex.org/W4382239442","https://openalex.org/W4384918448","https://openalex.org/W4385569882","https://openalex.org/W4385570777","https://openalex.org/W4385574101","https://openalex.org/W4385893817","https://openalex.org/W4386798159","https://openalex.org/W4386907423","https://openalex.org/W4387031532","https://openalex.org/W4387321091","https://openalex.org/W4389518789","https://openalex.org/W4389520103","https://openalex.org/W4389524176","https://openalex.org/W4391528738","https://openalex.org/W4392224187","https://openalex.org/W4392637287","https://openalex.org/W4393159512","https://openalex.org/W4401042371","https://openalex.org/W4402671983","https://openalex.org/W4402684036","https://openalex.org/W4404021177","https://openalex.org/W4404087975","https://openalex.org/W4405219153","https://openalex.org/W4409362346","https://openalex.org/W4412377856","https://openalex.org/W6891899249"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4,41],"shown":[5],"impressive":[6],"capabilities":[7],"in":[8,56,169],"natural":[9],"language":[10],"processing":[11],"but":[12],"still":[13,51],"struggle":[14],"to":[15,44,61,128,133],"perform":[16],"well":[17],"on":[18,94],"knowledge-intensive":[19],"tasks":[20],"that":[21,119,163],"require":[22],"deep":[23],"reasoning":[24,152],"and":[25,38,90,124,148,159,172],"the":[26,80,84,88,91,110,117,120,134,138,151],"integration":[27],"of":[28,83,150],"external":[29,48,95,104],"knowledge.":[30],"Although":[31],"methods":[32],"such":[33],"as":[34],"Retrieval-Augmented":[35],"Generation":[36],"(RAG)":[37],"Chain-of-Thought":[39],"(CoT)":[40],"been":[42],"proposed":[43],"enhance":[45],"LLMs":[46,158],"with":[47],"knowledge,":[49,96,105],"they":[50],"suffer":[52],"from":[53],"internal":[54,99],"bias":[55],"LLMs,":[57],"which":[58,78],"often":[59],"leads":[60],"incorrect":[62],"answers.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67],"propose":[68],"a":[69],"novel":[70],"causal":[71,85,130],"prompting":[72],"framework,":[73],"Conditional":[74],"Front-Door":[75],"Prompting":[76],"(CFD-Prompting),":[77],"enables":[79],"unbiased":[81],"estimation":[82],"effect":[86],"between":[87],"query":[89,111,121],"answer,":[92],"conditional":[93,139],"while":[97],"mitigating":[98],"bias.":[100],"By":[101],"constructing":[102],"counterfactual":[103],"our":[106],"framework":[107],"simulates":[108],"how":[109],"behaves":[112],"under":[113,142],"varying":[114],"contexts,":[115],"addressing":[116],"challenge":[118],"is":[122,125],"fixed":[123],"not":[126],"amenable":[127],"direct":[129],"intervention.":[131],"Compared":[132],"standard":[135],"front-door":[136],"adjustment,":[137],"variant":[140],"operates":[141],"weaker":[143],"assumptions,":[144],"enhancing":[145],"both":[146,170],"robustness":[147],"generalisability":[149],"process.":[153],"Extensive":[154],"experiments":[155],"across":[156],"multiple":[157],"benchmark":[160],"datasets":[161],"demonstrate":[162],"CFD-Prompting":[164],"significantly":[165],"outperforms":[166],"existing":[167],"baselines":[168],"accuracy":[171],"robustness.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-11-08T00:00:00"}