{"id":"https://openalex.org/W7204190038","doi":"https://doi.org/10.1145/3799682.3841095","title":"SAFE-G: Structure-Aware Faithful Evidence-guided Generation for Knowledge-Based Visual Question Answering","display_name":"SAFE-G: Structure-Aware Faithful Evidence-guided Generation for Knowledge-Based Visual Question Answering","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7204190038","doi":"https://doi.org/10.1145/3799682.3841095"},"language":"en","primary_location":{"id":"doi:10.1145/3799682.3841095","doi":"https://doi.org/10.1145/3799682.3841095","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799682.3841095","pdf_url":null,"source":{"id":"https://openalex.org/S4393918199","display_name":"ACM International Conference on Information and Knowledge Management (CIKM)","issn_l":"2155-0751","issn":["2155-0751"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3799682.3841095","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130584880","display_name":"Long Shu","orcid":"https://orcid.org/0009-0003-8570-0814","observed_orcids":["https://orcid.org/0009-0003-8570-0814"]},"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":"Long Shu","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0003-8570-0814","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148065568","display_name":"Shuochen Liu","orcid":"https://orcid.org/0000-0003-4724-8989","observed_orcids":["https://orcid.org/0000-0003-4724-8989"]},"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":"Shuochen Liu","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-4724-8989","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148164256","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0003-4700-2612","observed_orcids":["https://orcid.org/0000-0003-4700-2612"]},"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":"Wei Chen","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-4700-2612","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148170786","display_name":"Junda Lin","orcid":"https://orcid.org/0009-0008-6599-5981","observed_orcids":["https://orcid.org/0009-0008-6599-5981"]},"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":"Junda Lin","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0008-6599-5981","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133748281","display_name":"Zhi Zheng","orcid":"https://orcid.org/0000-0001-7758-8904","observed_orcids":["https://orcid.org/0000-0001-7758-8904"]},"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":"Zhi Zheng","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0001-7758-8904","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134186853","display_name":"HuiJun Hou","orcid":"https://orcid.org/0009-0003-8764-6938","observed_orcids":["https://orcid.org/0009-0003-8764-6938"]},"institutions":[{"id":"https://openalex.org/I4401726823","display_name":"Nio (China)","ror":"https://ror.org/02w12zj89","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726823"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huijun Hou","raw_affiliation_strings":["NIO, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-8764-6938","affiliations":[{"raw_affiliation_string":"NIO, Shanghai, China","institution_ids":["https://openalex.org/I4401726823"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148081345","display_name":"Tong Xu","orcid":"https://orcid.org/0000-0003-4246-5386","observed_orcids":["https://orcid.org/0000-0003-4246-5386"]},"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":"Tong Xu","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-4246-5386","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64616395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4337","last_page":"4348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":9.999999747378752e-05,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0,"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/knowledge-based-visual-question-answering","display_name":"knowledge-based visual question answering","score":0.9980000257492065},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.7670000195503235},{"id":"https://openalex.org/keywords/graph-retrieval","display_name":"graph retrieval","score":0.722000002861023},{"id":"https://openalex.org/keywords/reinforcement-learning-for-reasoning","display_name":"reinforcement learning for reasoning","score":0.5149999856948853},{"id":"https://openalex.org/keywords/external-knowledge-retrieval","display_name":"external knowledge retrieval","score":0.6830000281333923},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"noise reduction","score":0.5580000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8057000041007996},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6967999935150146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5705999732017517},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5447999835014343},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4887999892234802},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.453000009059906},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4226999878883362},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3855000138282776},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36959999799728394},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3208000063896179},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2818000018596649},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27090001106262207},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3799682.3841095","doi":"https://doi.org/10.1145/3799682.3841095","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799682.3841095","pdf_url":null,"source":{"id":"https://openalex.org/S4393918199","display_name":"ACM International Conference on Information and Knowledge Management (CIKM)","issn_l":"2155-0751","issn":["2155-0751"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.21796","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21796","pdf_url":"https://arxiv.org/pdf/2608.21796","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.21796","doi":"https://doi.org/10.48550/arxiv.2608.21796","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.21796","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3799682.3841095","doi":"https://doi.org/10.1145/3799682.3841095","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799682.3841095","pdf_url":null,"source":{"id":"https://openalex.org/S4393918199","display_name":"ACM International Conference on Information and Knowledge Management (CIKM)","issn_l":"2155-0751","issn":["2155-0751"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204190038.pdf","grobid_xml":"https://content.openalex.org/works/W7204190038.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4414884276","https://openalex.org/W7171446319","https://openalex.org/W4416948262","https://openalex.org/W4415947137","https://openalex.org/W7171448319","https://openalex.org/W7148640556","https://openalex.org/W3044175177","https://openalex.org/W7213421952","https://openalex.org/W7117103074","https://openalex.org/W4416059506"],"abstract_inverted_index":{"Knowledge-based":[0],"Visual":[1],"Question":[2],"Answering":[3],"(KB-VQA)":[4],"aims":[5],"to":[6,26,37,49,56,64,73,111,127,149,166,178],"answer":[7],"queries":[8],"that":[9,66,123,146,197],"necessitate":[10],"reasoning":[11,68,213],"over":[12],"external":[13,28],"knowledge":[14],"sources":[15],"beyond":[16],"the":[17,41,67,74,154,164,171,191,211],"visual":[18,107],"content.":[19],"Typically,":[20],"current":[21],"methods":[22,46,201],"fuse":[23],"multimodal":[24,182],"features":[25,183],"retrieve":[27],"information,":[29],"subsequently":[30,116],"leveraging":[31],"Multimodal":[32],"Large":[33],"Language":[34],"Models":[35],"(MLLMs)":[36],"derive":[38],"answers":[39,151],"from":[40],"retrieved":[42,75,172],"evidence.":[43,76,133],"However,":[44],"these":[45,79],"often":[47],"struggle":[48],"capture":[50],"structural":[51,125],"associations":[52],"within":[53],"complex":[54],"contexts":[55],"effectively":[57,174],"filter":[58,128],"noise.":[59],"Furthermore,":[60],"they":[61],"frequently":[62],"fail":[63],"ensure":[65],"process":[69],"remains":[70],"strictly":[71],"faithful":[72,186],"To":[77],"address":[78],"challenges,":[80],"we":[81,99,135],"propose":[82],"SAFE-G,":[83],"a":[84,102,118,137,203],"Structure-Aware":[85],"Faithful":[86],"Evidence-guided":[87],"Generation":[88],"framework,":[89],"which":[90],"enables":[91],"precise":[92,132],"evidence":[93,156,180],"localization":[94],"and":[95,108,115,130,184,193,207],"trustworthy":[96],"reasoning.":[97,187],"Specifically,":[98],"first":[100],"employ":[101],"coarse-grained":[103],"hybrid":[104],"search":[105],"fusing":[106],"textual":[109],"modalities":[110],"recall":[112],"candidate":[113],"documents,":[114],"implement":[117],"structure-aware":[119],"fine-grained":[120],"graph":[121],"retrieval":[122],"captures":[124],"dependencies":[126],"noise":[129],"pinpoint":[131],"Moreover,":[134],"introduce":[136],"reinforcement":[138],"learning":[139],"(RL)":[140],"strategy":[141],"with":[142],"an":[143],"evidence-grounded":[144],"reward":[145],"assigns":[147],"credit":[148],"correct":[150],"only":[152],"when":[153],"selected":[155],"is":[157,218],"correct.":[158],"This":[159],"strict":[160],"alignment":[161],"constraint":[162],"compels":[163],"model":[165],"anchor":[167],"its":[168,176],"response":[169],"in":[170],"context,":[173],"enhancing":[175,210],"capability":[177],"locate":[179],"via":[181],"perform":[185],"Extensive":[188],"experiments":[189],"on":[190],"Encyclopedic-VQA":[192],"InfoSeek":[194],"benchmarks":[195],"demonstrate":[196],"SAFE-G":[198],"outperforms":[199],"prior":[200],"by":[202],"margin":[204],"of":[205],"8.9%":[206],"3.5%,":[208],"substantially":[209],"overall":[212],"accuracy.":[214],"Our":[215],"source":[216],"code":[217],"publicly":[219],"available":[220],"at:":[221],"https://github.com/MINE-USTC/SAFE-G.":[222]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-08-26T00:00:00"}