{"id":"https://openalex.org/W4415036368","doi":"https://doi.org/10.18653/v1/2026.acl-long.612","title":"Reinforced Informativeness Optimization for Long-Form Retrieval-Augmented Generation","display_name":"Reinforced Informativeness Optimization for Long-Form Retrieval-Augmented Generation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415036368","doi":"https://doi.org/10.18653/v1/2026.acl-long.612"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.612","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.612","pdf_url":"https://aclanthology.org/2026.acl-long.612.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.612.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100370095","display_name":"Yuhao Wang","orcid":"https://orcid.org/0009-0001-5760-9285"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhao Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074848230","display_name":"Ruiyang Ren","orcid":"https://orcid.org/0000-0002-0562-9911"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruiyang Ren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070997816","display_name":"Yucheng Wang","orcid":"https://orcid.org/0009-0007-8940-5133"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yucheng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037145565","display_name":"Wayne Xin Zhao","orcid":"https://orcid.org/0000-0002-8333-6196"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375136","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-4690-1886"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112985399","display_name":"Hua Wu","orcid":"https://orcid.org/0000-0001-8254-1561"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hua Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100386385","display_name":"Haifeng Wang","orcid":"https://orcid.org/0000-0001-5381-1657"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haifeng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.00808069,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13393","last_page":"13406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9344000220298767,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9344000220298767,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6596999764442444},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6365000009536743},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.5902000069618225},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.4174000024795532},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3718999922275543},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.3149000108242035},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.2955000102519989}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.771399974822998},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6596999764442444},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6365000009536743},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.5902000069618225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4966000020503998},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4805999994277954},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.27149999141693115},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.612","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.612","pdf_url":"https://aclanthology.org/2026.acl-long.612.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.20825","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.20825","pdf_url":"https://arxiv.org/pdf/2505.20825","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,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.20825","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.20825","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,"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.612","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.612","pdf_url":"https://aclanthology.org/2026.acl-long.612.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4128466783","display_name":null,"funder_award_id":"92470205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415036368.pdf","grobid_xml":"https://content.openalex.org/works/W4415036368.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Long-form":[0],"question":[1],"answering":[2],"(LFQA)":[3],"requires":[4],"open-ended":[5],"long-form":[6,162],"responses":[7],"that":[8,115,145],"synthesize":[9],"coherent,":[10],"factually":[11],"grounded":[12],"content":[13],"from":[14],"multi-source":[15],"evidence.This":[16],"makes":[17],"reinforcement":[18],"learning":[19],"(RL)":[20],"reward":[21,24,65,117,155],"design":[22],"critical.The":[23],"must":[25],"be":[26],"verifiable":[27,64,81,92,138,154],"for":[28,79,94,126,160],"faithful":[29],"grounding":[30],"and":[31,51,71,90,109,119,130,142,151],"stable":[32],"optimization.However,":[33],"many":[34],"standard":[35],"rewards":[36,114],"assume":[37],"a":[38,57,77,88,158],"unique":[39],"target":[40],"with":[41,100],"an":[42],"exact-match":[43],"notion":[44],"of":[45,106],"correctness,":[46],"which":[47],"fits":[48],"short-form":[49],"QA":[50],"math":[52],"but":[53],"breaks":[54],"in":[55],"LFQA.As":[56],"result,":[58],"current":[59],"RAG":[60],"systems":[61],"still":[62],"lack":[63],"mechanisms,":[66],"yielding":[67],"unstable":[68],"feedback":[69],"signals":[70],"suboptimal":[72],"optimization":[73],"outcomes.We":[74],"propose":[75],"RioRAG,":[76],"framework":[78],"reinforced":[80],"informativeness":[82,86],"optimization.First,":[83],"it":[84],"defines":[85],"as":[87,157],"measurable":[89],"externally":[91,137],"objective":[93],"RL.Second,":[95],"RioRAG":[96,146],"uses":[97],"nugget-centric":[98],"verification":[99],"cross-source":[101],"checks":[102],"to":[103,110],"enable":[104],"self-evolution":[105],"smaller":[107],"LLMs":[108],"provide":[111],"denser,":[112],"actiondiscriminative":[113],"mitigate":[116],"sparsity":[118],"stabilize":[120],"optimization.This":[121],"formulation":[122],"avoids":[123],"handcrafted":[124],"supervision":[125],"the":[127],"policy":[128],"model":[129],"strong":[131],"teacher-model":[132],"distillation,":[133],"relying":[134],"instead":[135],"on":[136,140],"feedback.Experiments":[139],"LongFact":[141],"RAGChecker":[143],"show":[144],"achieves":[147],"higher":[148],"factual":[149],"recall":[150],"faithfulness,":[152],"establishing":[153],"modeling":[156],"foundation":[159],"trustworthy":[161],"RAG.Our":[163],"codes":[164],"are":[165],"available":[166],"at":[167],"https://github.com/RUCAIBox/":[168],"RioRAG.":[169]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}