{"id":"https://openalex.org/W4414812773","doi":"https://doi.org/10.18653/v1/2026.acl-long.829","title":"Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering","display_name":"Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4414812773","doi":"https://doi.org/10.18653/v1/2026.acl-long.829"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.829","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.829","pdf_url":"https://aclanthology.org/2026.acl-long.829.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.829.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023724440","display_name":"Huiyao Chen","orcid":"https://orcid.org/0000-0003-3518-0817"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huiyao Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062124960","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0003-3964-2433"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100655638","display_name":"Yinghui Li","orcid":"https://orcid.org/0000-0003-4124-2391"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yinghui Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004953265","display_name":"Meishan Zhang","orcid":"https://orcid.org/0000-0001-6335-1340"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meishan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Baotian Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baotian Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Min Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Zhang","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":21.2894,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9663794,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"18176","last_page":"18198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9965000152587891,"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":0.9965000152587891,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.957099974155426,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13274","display_name":"Expert finding and Q&A systems","score":0.944100022315979,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/question-answering","display_name":"Question answering","score":0.6625999808311462},{"id":"https://openalex.org/keywords/rhetorical-question","display_name":"Rhetorical question","score":0.6071000099182129},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5823000073432922},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4332999885082245},{"id":"https://openalex.org/keywords/argumentative","display_name":"Argumentative","score":0.3946000039577484},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.36640000343322754},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.366100013256073},{"id":"https://openalex.org/keywords/mean-reciprocal-rank","display_name":"Mean reciprocal rank","score":0.3659999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7703999876976013},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6625999808311462},{"id":"https://openalex.org/C192562157","wikidata":"https://www.wikidata.org/wiki/Q316694","display_name":"Rhetorical question","level":2,"score":0.6071000099182129},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5823000073432922},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5356000065803528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5239999890327454},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4332999885082245},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3970000147819519},{"id":"https://openalex.org/C2781306805","wikidata":"https://www.wikidata.org/wiki/Q4789761","display_name":"Argumentative","level":2,"score":0.3946000039577484},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C44083865","wikidata":"https://www.wikidata.org/wiki/Q3853443","display_name":"Mean reciprocal rank","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C179139399","wikidata":"https://www.wikidata.org/wiki/Q1228944","display_name":"Domain of discourse","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2800999879837036},{"id":"https://openalex.org/C84389358","wikidata":"https://www.wikidata.org/wiki/Q1129466","display_name":"Discourse analysis","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.25440001487731934}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.829","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.829","pdf_url":"https://aclanthology.org/2026.acl-long.829.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:2506.06313","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2506.06313","pdf_url":"https://arxiv.org/pdf/2506.06313","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.06313","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.06313","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":null,"license_id":null,"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.829","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.829","pdf_url":"https://aclanthology.org/2026.acl-long.829.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/G1883487206","display_name":null,"funder_award_id":"62336008","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/W4414812773.pdf","grobid_xml":"https://content.openalex.org/works/W4414812773.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"long-document":[1],"question":[2,39],"answering":[3],"systems":[4],"typically":[5],"process":[6],"texts":[7],"as":[8],"flat":[9],"sequences":[10],"or":[11],"use":[12],"heuristic":[13],"chunking,":[14],"which":[15],"overlook":[16],"the":[17,91,101],"discourse":[18,43,65,73,94],"structures":[19],"that":[20,30],"naturally":[21],"guide":[22],"human":[23],"comprehension.We":[24],"present":[25],"a":[26],"discourse-aware":[27],"hierarchical":[28,78],"framework":[29,59,103],"leverages":[31],"rhetorical":[32],"structure":[33],"theory":[34],"(RST)":[35],"for":[36,67],"long":[37],"document":[38,109],"answering.Our":[40],"approach":[41],"converts":[42],"trees":[44],"into":[45],"sentence-level":[46],"representations":[47,52],"and":[48,56,76,99,111],"employs":[49],"LLM-enhanced":[50],"node":[51],"to":[53],"bridge":[54],"structural":[55],"semantic":[57],"information.The":[58],"involves":[60],"three":[61],"key":[62],"innovations:":[63],"language-universal":[64],"parsing":[66],"lengthy":[68],"documents,":[69],"LLM-based":[70],"enhancement":[71],"of":[72,93],"relation":[74],"nodes,":[75],"structure-guided":[77],"retrieval.Extensive":[79],"experiments":[80],"on":[81],"four":[82],"datasets":[83],"demonstrate":[84],"consistent":[85],"improvements":[86],"over":[87],"existing":[88],"approaches":[89],"through":[90],"incorporation":[92],"structure,":[95],"across":[96,107],"multiple":[97],"genres":[98],"languages.Moreover,":[100],"proposed":[102],"exhibits":[104],"strong":[105],"robustness":[106],"diverse":[108],"types":[110],"linguistic":[112],"settings.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}