{"id":"https://openalex.org/W4402351842","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651167","title":"Mitigating Knowledge Conflicts in Data-to-Text Generation via the Internalization of Fact Extraction","display_name":"Mitigating Knowledge Conflicts in Data-to-Text Generation via the Internalization of Fact Extraction","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351842","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651167"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10651167","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","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/A5101087836","display_name":"Xianjie Mo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianjie Mo","raw_affiliation_strings":["CAS,Institute of Computing Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS,Institute of Computing Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051936733","display_name":"Yang Xiang","orcid":"https://orcid.org/0000-0001-6104-1875"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Xiang","raw_affiliation_strings":["Peng Cheng Laboratory,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory,Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004433495","display_name":"Youcheng Pan","orcid":"https://orcid.org/0000-0002-8270-5455"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youcheng Pan","raw_affiliation_strings":["Peng Cheng Laboratory,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory,Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027262293","display_name":"Yongshuai Hou","orcid":"https://orcid.org/0000-0001-6994-8295"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongshuai Hou","raw_affiliation_strings":["Peng Cheng Laboratory,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory,Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100752685","display_name":"Ping Luo","orcid":"https://orcid.org/0000-0002-6645-4721"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Luo","raw_affiliation_strings":["CAS,Institute of Computing Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS,Institute of Computing Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3055,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64393257,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9986000061035156,"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/internalization","display_name":"Internalization","score":0.7638866901397705},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6458548903465271},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.5419950485229492},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.49765756726264954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29882678389549255},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.10507053136825562},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.06405577063560486}],"concepts":[{"id":"https://openalex.org/C139770010","wikidata":"https://www.wikidata.org/wiki/Q1339807","display_name":"Internalization","level":3,"score":0.7638866901397705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6458548903465271},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.5419950485229492},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.49765756726264954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29882678389549255},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.10507053136825562},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.06405577063560486},{"id":"https://openalex.org/C1491633281","wikidata":"https://www.wikidata.org/wiki/Q7868","display_name":"Cell","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10651167","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"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/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2560674852","https://openalex.org/W2606974598","https://openalex.org/W2905103081","https://openalex.org/W2952809536","https://openalex.org/W2962985882","https://openalex.org/W2963532001","https://openalex.org/W2989743967","https://openalex.org/W2997852611","https://openalex.org/W3034999214","https://openalex.org/W3100560913","https://openalex.org/W3103733040","https://openalex.org/W3169841173","https://openalex.org/W3170180819","https://openalex.org/W3174887376","https://openalex.org/W3175218683","https://openalex.org/W3175443153","https://openalex.org/W3177813494","https://openalex.org/W3212618200","https://openalex.org/W4210451781","https://openalex.org/W4221143046","https://openalex.org/W4285174063","https://openalex.org/W4288089799","https://openalex.org/W4292122324","https://openalex.org/W4322718191","https://openalex.org/W4377865924","https://openalex.org/W4379087871","https://openalex.org/W4384642600","https://openalex.org/W4385245566","https://openalex.org/W4385571944","https://openalex.org/W4385572448","https://openalex.org/W4385573588","https://openalex.org/W4385574183","https://openalex.org/W4389519364","https://openalex.org/W4389523675","https://openalex.org/W4401042371","https://openalex.org/W6682631176","https://openalex.org/W6757585730","https://openalex.org/W6769627184","https://openalex.org/W6773829392","https://openalex.org/W6787859630","https://openalex.org/W6796581206","https://openalex.org/W6798182279","https://openalex.org/W6809646742","https://openalex.org/W6841791078","https://openalex.org/W6850625674","https://openalex.org/W6853155250","https://openalex.org/W6853164727"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4366318089","https://openalex.org/W2068721292","https://openalex.org/W4225584766","https://openalex.org/W2145545797","https://openalex.org/W2764950946","https://openalex.org/W2952148578","https://openalex.org/W2014118959","https://openalex.org/W1585685362"],"abstract_inverted_index":{"Large":[0],"Language":[1,10],"Models":[2],"(LLMs)":[3],"have":[4],"made":[5],"remarkable":[6],"advancements":[7],"in":[8,55,226,272,290],"Natural":[9],"Generation.":[11],"Nonetheless,":[12],"LLMs":[13,45,71,96,136],"are":[14,160,236],"prone":[15],"to":[16,50,72,104,137,179,215],"encountering":[17],"knowledge":[18,67,158,292],"conflicts,":[19],"scenarios":[20],"where":[21,157],"the":[22,31,40,48,74,81,111,125,139,147,172,196,212,217,227,268,285],"generated":[23],"statement":[24],"exhibits":[25],"either":[26],"twisted":[27],"facts":[28,35,53,182,187],"that":[29,36,44,262],"contradict":[30],"source":[32],"or":[33],"unverified":[34],"lack":[37],"substantiation":[38],"from":[39,60],"source.":[41],"We":[42],"posit":[43],"should":[46],"possess":[47],"capability":[49],"differentiate":[51],"between":[52],"grounded":[54],"evidence":[56],"and":[57,115,183,205,234,247,255,277],"those":[58,98],"derived":[59],"inference.":[61],"A":[62],"promising":[63],"avenue":[64],"for":[65,93,195],"mitigating":[66,291],"conflicts":[68,159],"involves":[69],"prompting":[70],"externalize":[73],"multi-step":[75],"reasoning":[76,88],"during":[77,143],"text":[78,144,174,189,229,253,257],"generation":[79,145,175,230,242,254],"within":[80,146],"chain-of-thought":[82],"paradigm.":[83,150],"Nevertheless,":[84],"such":[85],"externalization":[86],"of":[87,127,274,287],"has":[89],"only":[90],"shown":[91],"benefits":[92],"sufficiently":[94],"large":[95,114],"(e.g.,":[97],"exceeding":[99],"100B":[100],"parameters).":[101],"Despite":[102],"attempts":[103],"distill":[105],"this":[106],"ability":[107,214],"into":[108],"smaller":[109,135],"LLMs,":[110],"reliance":[112],"on":[113,238],"inefficient":[116],"teacher":[117],"models":[118,152,178,266],"remains":[119],"a":[120],"necessity.":[121],"Thus,":[122],"we":[123,163],"introduce":[124],"Internalization":[126],"Fact":[128],"Extraction":[129],"(IFE),":[130],"which":[131],"optimizes":[132],"instruction-tuning,":[133],"empowering":[134],"internalize":[138,216],"fact":[140,167,198,218],"extraction":[141,168,199,219],"process":[142,220],"auxiliary":[148,166,192,197,210],"learning":[149],"Consequently,":[151],"can":[153],"directly":[154],"generate":[155],"statements":[156],"mitigated.":[161],"Specifically,":[162],"design":[164],"an":[165],"task":[169,200],"built":[170],"upon":[171],"primary":[173,228],"task,":[176],"requiring":[177],"identify":[180],"evidential":[181],"filter":[184],"out":[185],"inferential":[186],"after":[188],"generation.":[190,258],"The":[191],"training":[193],"dataset":[194],"was":[201],"constructed":[202],"using":[203],"word-stemming":[204],"string-matching":[206],"techniques.":[207],"By":[208],"leveraging":[209],"learning,":[211],"models\u2019":[213],"emerges,":[221],"thereby":[222],"enhancing":[223],"its":[224],"performance":[225],"task.":[231],"Extensive":[232],"experiments":[233],"analyses":[235],"conducted":[237],"three":[239],"benchmark":[240],"data-to-text":[241],"datasets":[243],"(i.e.,":[244],"FeTaQA,":[245],"DialogSum,":[246],"SAMSum),":[248],"covering":[249],"sub-tasks":[250],"including":[251],"table-based":[252],"dialogue-based":[256],"Experimental":[259],"results":[260],"show":[261],"our":[263],"IFE":[264,288],"instruction-tuned":[265,270],"outperform":[267],"vanilla":[269],"baselines":[271],"terms":[273],"both":[275],"factuality":[276],"quality":[278],"without":[279],"introducing":[280],"any":[281],"inference":[282],"latency,":[283],"demonstrating":[284],"superiority":[286],"instruction-tuning":[289],"conflicts.":[293]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}