{"id":"https://openalex.org/W7168355812","doi":"https://doi.org/10.1145/3805712.3809664","title":"Good Ranks Follow Good Answers: Unsupervised Answer-Driven Reranking for Multimodal Document QA","display_name":"Good Ranks Follow Good Answers: Unsupervised Answer-Driven Reranking for Multimodal Document QA","publication_year":2026,"publication_date":"2026-07-15","ids":{"openalex":"https://openalex.org/W7168355812","doi":"https://doi.org/10.1145/3805712.3809664"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809664","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809664","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":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809664","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140796190","display_name":"Keyu Zhu","orcid":"https://orcid.org/0009-0008-6256-8554"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210137491","display_name":"National Science Centre","ror":"https://ror.org/03ha2q922","country_code":"PL","type":"government","lineage":["https://openalex.org/I4210137491"]}],"countries":["CN","PL"],"is_corresponding":false,"raw_author_name":"Keyu Zhu","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China and Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, -\u9009\u62e9-, China"],"raw_orcid":"https://orcid.org/0009-0008-6256-8554","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China and Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, -\u9009\u62e9-, China","institution_ids":["https://openalex.org/I4210137491","https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140857037","display_name":"Shuanghong Shen","orcid":"https://orcid.org/0000-0003-3905-9352"},"institutions":[{"id":"https://openalex.org/I174385955","display_name":"Hefei Normal University","ror":"https://ror.org/01b64k086","country_code":"CN","type":"education","lineage":["https://openalex.org/I174385955"]},{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuanghong Shen","raw_affiliation_strings":["Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China and Guangdong Key Laboratory of Mental Health and Cognitive Science, South China Normal University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3905-9352","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China and Guangdong Key Laboratory of Mental Health and Cognitive Science, South China Normal University, Guangzhou, China","institution_ids":["https://openalex.org/I187400657","https://openalex.org/I174385955"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140850693","display_name":"Xianquan Wang","orcid":"https://orcid.org/0009-0003-9744-220X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianquan Wang","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-9744-220X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140926525","display_name":"Kai Zhang","orcid":"https://orcid.org/0000-0001-5335-2470"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Zhang","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, -\u9009\u62e9-, China"],"raw_orcid":"https://orcid.org/0000-0001-5335-2470","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, -\u9009\u62e9-, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140957495","display_name":"Shijin Wang","orcid":"https://orcid.org/0000-0002-9202-7678"},"institutions":[{"id":"https://openalex.org/I4210159484","display_name":"Ian's Friends Foundation","ror":"https://ror.org/05d56bw89","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210159484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shijin Wang","raw_affiliation_strings":["iFLYTEK AI Research & State Key Laboratory of Cognitive Intelligence, iFLYTEK, Co., Ltd, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-9202-7678","affiliations":[{"raw_affiliation_string":"iFLYTEK AI Research & State Key Laboratory of Cognitive Intelligence, iFLYTEK, Co., Ltd, Hefei, China","institution_ids":["https://openalex.org/I4210159484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140910722","display_name":"Qi Liu","orcid":"https://orcid.org/0000-0001-6956-5550"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Liu","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6956-5550","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140877245","display_name":"Zhenya Huang","orcid":"https://orcid.org/0000-0003-1661-0420"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenya Huang","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1661-0420","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2600","last_page":"2610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2896000146865845},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.23639999330043793},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.22920000553131104},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.22679999470710754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6255000233650208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5227000117301941},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.398499995470047},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2759999930858612},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.23639999330043793},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.23319999873638153},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.22920000553131104},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.22679999470710754},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.21950000524520874}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809664","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809664","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"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809664","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809664","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2507134384","https://openalex.org/W3021397474","https://openalex.org/W3120043490","https://openalex.org/W4287887100","https://openalex.org/W4297678984","https://openalex.org/W4385237494","https://openalex.org/W4389523765","https://openalex.org/W4400527956","https://openalex.org/W4402671970","https://openalex.org/W4411113299","https://openalex.org/W4412886806","https://openalex.org/W4412887933","https://openalex.org/W4412888671","https://openalex.org/W4412889737","https://openalex.org/W4415796209","https://openalex.org/W4415797289","https://openalex.org/W4416034014","https://openalex.org/W4416036933","https://openalex.org/W7108329187","https://openalex.org/W7160140380","https://openalex.org/W7160185532"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Document":[1],"Question":[2],"Answering":[3],"(MDQA)":[4],"systems":[5],"commonly":[6],"follow":[7],"a":[8,65,91,96,102],"retrieve-then-answer":[9],"paradigm;":[10],"however,":[11],"the":[12,82,122,165,176],"retrieval":[13],"stage":[14],"often":[15],"introduces":[16],"substantial":[17],"noise,":[18],"making":[19],"an":[20,85,148],"effective":[21,134],"reranking":[22,145],"component":[23],"indispensable.":[24],"Existing":[25],"reranker":[26,70,83,180],"training":[27,71],"frameworks":[28],"in":[29],"MDQA":[30,156],"rely":[31],"predominantly":[32],"on":[33],"proxy":[34,73],"supervision":[35],"derived":[36],"from":[37,72],"human":[38],"annotations":[39],"or":[40],"large":[41],"language":[42],"model":[43],"(LLM)":[44],"outputs,":[45],"which":[46],"are":[47],"frequently":[48],"noisy":[49],"and,":[50],"more":[51],"critically,":[52],"misaligned":[53],"with":[54,90,116],"downstream":[55,92,117],"answer":[56,108],"quality.":[57],"To":[58,120],"overcome":[59],"this":[60],"limitation,":[61],"we":[62,80,124],"propose":[63],"AD-Reranker,":[64],"novel":[66],"framework":[67],"that":[68,88,106,141],"shifts":[69],"imitation":[74],"to":[75],"answer-driven":[76,179],"utility":[77],"optimization.":[78],"Specifically,":[79],"reformulate":[81],"as":[84,95],"environment-grounded":[86],"agent":[87],"interacts":[89],"reader,":[93],"modeled":[94],"deterministic":[97],"environment.":[98],"We":[99],"further":[100],"design":[101],"composite":[103],"reward":[104],"function":[105],"integrates":[107],"correctness,":[109],"thereby":[110],"explicitly":[111],"incentivizing":[112],"ranking":[113],"strategies":[114],"aligned":[115],"task":[118],"performance.":[119],"optimize":[121],"agent,":[123],"adopt":[125],"Group":[126],"Relative":[127],"Policy":[128],"Optimization":[129],"(GRPO),":[130],"enabling":[131],"stable":[132],"and":[133,147],"group-wise":[135],"policy":[136],"learning.":[137],"Empirical":[138],"results":[139],"demonstrate":[140],"AD-Reranker":[142,158],"achieves":[143],"superior":[144],"quality":[146],"optimal":[149],"accuracy-efficiency":[150],"trade-off.":[151],"When":[152],"integrated":[153],"into":[154],"standard":[155],"pipelines,":[157],"improves":[159],"accuracy":[160],"by":[161,170],"1.9%\u20135.0%":[162],"while":[163],"reducing":[164],"reader's":[166],"context":[167],"token":[168],"consumption":[169],"15%\u201352%,":[171],"providing":[172],"strong":[173],"evidence":[174],"for":[175],"effectiveness":[177],"of":[178],"training.":[181]},"counts_by_year":[],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2026-07-16T00:00:00"}