{"id":"https://openalex.org/W7152512634","doi":"https://doi.org/10.1145/3774904.3792524","title":"OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAG","display_name":"OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAG","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7152512634","doi":"https://doi.org/10.1145/3774904.3792524"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792524","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792524","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 ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792524","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048033573","display_name":"Fengran Mo","orcid":"https://orcid.org/0000-0002-0838-6994"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Fengran Mo","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada"],"raw_orcid":"https://orcid.org/0000-0002-0838-6994","affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133304562","display_name":"Zhan Su","orcid":"https://orcid.org/0000-0001-5189-9165"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhan Su","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada"],"raw_orcid":"https://orcid.org/0000-0001-5189-9165","affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103129849","display_name":"Yuchen Hui","orcid":"https://orcid.org/0000-0002-9659-3714"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yuchen Hui","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada"],"raw_orcid":"https://orcid.org/0000-0002-9659-3714","affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133277656","display_name":"Jinghan Zhang","orcid":"https://orcid.org/0009-0001-0999-270X"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinghan Zhang","raw_affiliation_strings":["Clemson University, Clemson, South Carolina, USA"],"raw_orcid":"https://orcid.org/0009-0001-0999-270X","affiliations":[{"raw_affiliation_string":"Clemson University, Clemson, South Carolina, USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123118762","display_name":"Jia Ao Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jia Ao Sun","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada"],"raw_orcid":"https://orcid.org/0000-0002-8340-155X","affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038767043","display_name":"Zheyuan Liu","orcid":"https://orcid.org/0000-0001-7809-4586"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheyuan Liu","raw_affiliation_strings":["University of Notre Dame, Notre Dame, Indiana, USA"],"raw_orcid":"https://orcid.org/0000-0001-7809-4586","affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, Indiana, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0003-3009-598X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":"https://orcid.org/0000-0003-3009-598X","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133307827","display_name":"Tetsuya Sakai","orcid":"https://orcid.org/0000-0002-6720-963X"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Sakai","raw_affiliation_strings":["Waseda University, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-6720-963X","affiliations":[{"raw_affiliation_string":"Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129685128","display_name":"Jian-Yun Nie","orcid":null},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jian-Yun Nie","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada"],"raw_orcid":"https://orcid.org/0000-0003-1556-3335","affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.51745103,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2252","last_page":"2262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.23929999768733978,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.23929999768733978,"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/T10028","display_name":"Topic Modeling","score":0.18160000443458557,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.10719999670982361,"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/decoding-methods","display_name":"Decoding methods","score":0.5430999994277954},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4325999915599823},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4325000047683716},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.34950000047683716},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.29280000925064087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7039999961853027},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5430999994277954},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5212000012397766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45559999346733093},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4325999915599823},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4325000047683716},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27149999141693115},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2644999921321869},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792524","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792524","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 ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792524","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792524","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 ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5369470715522766,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2889787757","https://openalex.org/W2912924812","https://openalex.org/W2963339397","https://openalex.org/W3099700870","https://openalex.org/W3115947671","https://openalex.org/W4226107163","https://openalex.org/W4385569686","https://openalex.org/W4385570777","https://openalex.org/W4389518671","https://openalex.org/W4389519928","https://openalex.org/W4389523765","https://openalex.org/W4400526199","https://openalex.org/W4402671783","https://openalex.org/W4403899386","https://openalex.org/W4407953323","https://openalex.org/W4409158071","https://openalex.org/W4409362817","https://openalex.org/W4409657405","https://openalex.org/W4410502462","https://openalex.org/W4411638716","https://openalex.org/W4412377123","https://openalex.org/W4412377217","https://openalex.org/W4412377794","https://openalex.org/W4412673524"],"related_works":[],"abstract_inverted_index":{"The":[0,22,159],"development":[1],"of":[2,14,24,32,39,73,94,114,138,143,172,190,200],"large":[3],"language":[4],"models":[5],"(LLMs)":[6],"has":[7],"achieved":[8],"superior":[9],"performance":[10,156],"in":[11,48,98],"a":[12,70,107,128],"range":[13],"downstream":[15],"tasks,":[16],"including":[17],"LLM-based":[18],"retrieval-augmented":[19],"generation":[20],"(RAG).":[21],"quality":[23,119],"generated":[25],"content":[26],"heavily":[27],"relies":[28],"on":[29,78,162],"the":[30,33,37,56,62,65,79,82,92,95,115,167,188],"usefulness":[31],"retrieved":[34,57,66,96,116],"information":[35,42,58,67,97,117,146],"and":[36,75,81,153,169,195],"capacity":[38],"LLMs'":[40],"internal":[41],"processing":[43],"mechanism":[44],"to":[45,61,88,126,135,184],"incorporate":[46],"it":[47],"answer":[49,99],"generation.":[50,100,123],"It":[51,85],"is":[52,59,86,132,182],"generally":[53],"assumed":[54],"that":[55,110,131],"relevant":[60],"question.":[63],"However,":[64],"may":[68],"have":[69],"variable":[71],"degree":[72],"relevance":[74,93,149],"usefulness,":[76],"depending":[77],"question":[80],"document":[83],"collection.":[84],"important":[87],"take":[89],"into":[90],"account":[91],"In":[101],"this":[102,180],"paper,":[103],"we":[104],"propose":[105],"OpenDecoder,":[106],"new":[108],"approach":[109],"leverages":[111],"explicit":[112,144],"evaluation":[113,145],"as":[118],"indicator":[120],"features":[121],"for":[122,192],"We":[124],"aim":[125],"build":[127],"RAG":[129],"model":[130],"more":[133],"robust":[134],"varying":[136],"levels":[137],"noisy":[139],"context.":[140],"Three":[141],"types":[142],"are":[147],"considered:":[148],"score,":[150,152],"ranking":[151],"QPP":[154],"(query":[155],"prediction)":[157],"score.":[158],"experimental":[160],"results":[161],"five":[163],"benchmark":[164],"datasets":[165],"demonstrate":[166],"effectiveness":[168],"better":[170],"robustness":[171],"OpenDecoder":[173],"by":[174],"outperforming":[175],"various":[176],"baseline":[177],"methods.":[178],"Importantly,":[179],"paradigm":[181],"flexible":[183],"be":[185],"integrated":[186],"with":[187,197],"post-training":[189],"LLMs":[191],"any":[193,198],"purposes":[194],"incorporated":[196],"type":[199],"external":[201],"indicators.":[202]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-10T00:00:00"}