{"id":"https://openalex.org/W4401864068","doi":"https://doi.org/10.1145/3637528.3671847","title":"A Hierarchical Context Augmentation Method to Improve Retrieval-Augmented LLMs on Scientific Papers","display_name":"A Hierarchical Context Augmentation Method to Improve Retrieval-Augmented LLMs on Scientific Papers","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401864068","doi":"https://doi.org/10.1145/3637528.3671847"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671847","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/A5009736264","display_name":"Tian-Yi Che","orcid":"https://orcid.org/0000-0002-9383-4092"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tian-Yi Che","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017626590","display_name":"Xian-Ling Mao","orcid":"https://orcid.org/0000-0001-6795-2311"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian-Ling Mao","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101523733","display_name":"Tian Lan","orcid":"https://orcid.org/0000-0002-5200-1537"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Lan","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087631670","display_name":"Heyan Huang","orcid":"https://orcid.org/0000-0002-0320-7520"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heyan Huang","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009736264"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":1.0294,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.8051544,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"243","last_page":"254"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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":0.998199999332428,"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":0.996399998664856,"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":0.9919000267982483,"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/context","display_name":"Context (archaeology)","score":0.6941929459571838},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6438615322113037},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4035482704639435},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35853028297424316},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.15170538425445557},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.05840706825256348}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6941929459571838},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6438615322113037},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4035482704639435},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35853028297424316},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.15170538425445557},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.05840706825256348}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3671847","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2168859760","https://openalex.org/W2292995526","https://openalex.org/W2963718112","https://openalex.org/W2970771982","https://openalex.org/W3034364750","https://openalex.org/W3095220389","https://openalex.org/W3185341429","https://openalex.org/W4252076394","https://openalex.org/W4309674289","https://openalex.org/W4323345796","https://openalex.org/W4394707752"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Scientific":[0],"papers":[1],"of":[2,12,19,74,88,111,125,133,150,167,182,198,206,223],"a":[3,10,96,126,154,174],"large":[4],"scale":[5,166],"on":[6,210,226,255],"the":[7,17,71,85,108,117,122,130,165,180,195,204,216,221],"Internet":[8],"encompass":[9],"wealth":[11],"data":[13],"and":[14,39,76,128,141,190,239],"knowledge,":[15,26,69],"attracting":[16],"attention":[18],"numerous":[20],"researchers.":[21],"To":[22,90],"fully":[23],"utilize":[24,116],"these":[25],"Retrieval-Augmented":[27,103,224],"Large":[28],"Language":[29],"Models":[30],"(LLMs)":[31],"usually":[32],"leverage":[33],"large-scale":[34],"scientific":[35,112,134,212],"corpus":[36],"to":[37,47,83,105,120,162,178,201],"train":[38],"then":[40],"retrieve":[41],"relevant":[42],"passages":[43,200],"from":[44,136],"external":[45],"memory":[46],"improve":[48],"generation,":[49],"which":[50,79,101,158],"have":[51],"demonstrated":[52],"outstanding":[53],"performance.":[54],"However,":[55],"existing":[56],"methods":[57],"can":[58,159],"only":[59],"capture":[60],"one-dimension":[61],"fragmented":[62],"textual":[63,185],"information":[64,132,197],"without":[65],"incorporating":[66],"hierarchical":[67,97,123],"structural":[68,169],"eg.":[70],"deduction":[72],"relationship":[73,124],"abstract":[75],"main":[77],"body,":[78],"makes":[80],"it":[81,243],"difficult":[82],"grasp":[84],"central":[86],"thought":[87],"papers.":[89,113],"tackle":[91],"this":[92],"problem,":[93],"we":[94,115,145,172,193],"propose":[95,173],"context":[98,135,183],"augmentation":[99],"method,":[100],"helps":[102],"LLMs":[104,225],"autoregressively":[106],"learn":[107],"structure":[109,131,181,205],"knowledge":[110],"Specifically,":[114],"document":[118,151],"tree":[119,152],"represent":[121,179],"paper":[127],"enhance":[129,203],"three":[137,211],"aspects:":[138],"scale,":[139],"format":[140,177],"global":[142,196],"information.":[143],"First,":[144],"think":[146],"each":[147],"top-bottom":[148],"path":[149],"is":[153],"logical":[155],"independent":[156],"context,":[157],"be":[160],"used":[161],"largely":[163],"increase":[164],"extracted":[168],"corpus.":[170],"Second,":[171],"novel":[175],"label-based":[176],"in":[184,235],"sequences,":[186],"unified":[187],"between":[188],"training":[189],"inference.":[191],"Third,":[192],"introduce":[194],"retrieved":[199],"further":[202],"context.":[207],"Extensive":[208],"experiments":[209],"tasks":[213],"show":[214],"that":[215],"proposed":[217],"method":[218,231],"significantly":[219],"improves":[220],"performance":[222,234],"all":[227],"tasks.":[228],"Besides,":[229],"our":[230],"achieves":[232],"start-of-art":[233],"Question":[236],"Answer":[237],"task":[238],"outperforms":[240],"ChatGPT.":[241],"Moreover,":[242],"also":[244],"brings":[245],"considerate":[246],"gains":[247],"with":[248],"irrelevant":[249],"retrieval":[250],"passages,":[251],"illustrating":[252],"its":[253],"effectiveness":[254],"practical":[256],"application":[257],"scenarios.":[258]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-07T14:57:38.498316","created_date":"2025-10-10T00:00:00"}