{"id":"https://openalex.org/W4415797147","doi":"https://doi.org/10.52202/079017-1986","title":"Make Your LLM Fully Utilize the Context","display_name":"Make Your LLM Fully Utilize the Context","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4415797147","doi":"https://doi.org/10.52202/079017-1986"},"language":"en","primary_location":{"id":"doi:10.52202/079017-1986","doi":"https://doi.org/10.52202/079017-1986","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-1986","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2404.16811","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027673336","display_name":"Shengnan An","orcid":"https://orcid.org/0009-0003-4989-4607","observed_orcids":["https://orcid.org/0009-0003-4989-4607"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengnan An","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102574240","display_name":"Zexiong Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zexiong Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061546771","display_name":"Zeqi Lin","orcid":"https://orcid.org/0009-0001-2563-7601","observed_orcids":["https://orcid.org/0009-0001-2563-7601"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeqi Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Nanning Zheng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nanning Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025118710","display_name":"Jian\u2013Guang Lou","orcid":"https://orcid.org/0000-0001-8496-033X","observed_orcids":["https://orcid.org/0000-0001-8496-033X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian-Guang Lou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Weizhu Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weizhu Chen","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":15.591,"has_fulltext":true,"cited_by_count":54,"citation_normalized_percentile":{"value":0.99510194,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"62160","last_page":"62188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9735999703407288,"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":0.9735999703407288,"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":0.009200000204145908,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.006500000134110451,"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/large-language-models","display_name":"large language models","score":0.9929999709129333},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.6890000104904175},{"id":"https://openalex.org/keywords/context-length","display_name":"context length","score":0.39800000190734863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7832000255584717},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7472000122070312},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6814000010490417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45739999413490295},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.44190001487731934},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43369999527931213},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.35199999809265137},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34880000352859497},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C78780964","wikidata":"https://www.wikidata.org/wiki/Q7233193","display_name":"Position paper","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.31290000677108765},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C2781368080","wikidata":"https://www.wikidata.org/wiki/Q501688","display_name":"Context awareness","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2660999894142151},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2563000023365021},{"id":"https://openalex.org/C33326189","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information integration","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/079017-1986","doi":"https://doi.org/10.52202/079017-1986","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-1986","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2404.16811","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.16811","pdf_url":"https://arxiv.org/pdf/2404.16811","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,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2404.16811","doi":"https://doi.org/10.48550/arxiv.2404.16811","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2404.16811","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2404.16811","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.16811","pdf_url":"https://arxiv.org/pdf/2404.16811","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,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3833898155","display_name":null,"funder_award_id":"62088102","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/W4415797147.pdf","grobid_xml":"https://content.openalex.org/works/W4415797147.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4388748497","https://openalex.org/W4409363618","https://openalex.org/W4408355378","https://openalex.org/W4399913016","https://openalex.org/W4415795411","https://openalex.org/W4412945657","https://openalex.org/W4391876619","https://openalex.org/W7154171807","https://openalex.org/W4412945523","https://openalex.org/W4409362536"],"abstract_inverted_index":{"While":[0],"many":[1],"contemporary":[2],"large":[3],"language":[4],"models":[5],"(LLMs)":[6],"can":[7,51,168],"process":[8],"lengthy":[9],"input,":[10],"they":[11],"still":[12],"struggle":[13],"to":[14,42,69],"fully":[15],"utilize":[16],"information":[17,87,109,154,171],"within":[18,95],"the":[19,24,37,82,104,130,187],"long":[20,49,98,136],"context,":[21],"known":[22],"as":[23],"lost-in-the-middle":[25],"challenge.":[26],"We":[27],"hypothesize":[28],"that":[29,44,143,166],"it":[30],"stems":[31],"from":[32,110,172],"insufficient":[33],"explicit":[34],"supervision":[35],"during":[36],"long-context":[38,78,191],"training,":[39,64],"which":[40],"fails":[41],"emphasize":[43],"any":[45],"position":[46],"in":[47,175],"a":[48,65,76,90,96,201],"context":[50,99,146,178],"hold":[52],"crucial":[53],"information.":[54],"Based":[55],"on":[56,89,121,189,197,204,210],"this":[57,118],"intuition,":[58],"our":[59],"study":[60],"presents":[61],"information-intensive":[62,119],"(IN2)":[63],"purely":[66],"data-driven":[67],"solution":[68],"overcome":[70],"lost-in-the-middle.":[71],"Specifically,":[72],"IN2":[73],"training":[74,120],"leverages":[75],"synthesized":[77,97],"question-answer":[79],"dataset,":[80],"where":[81],"answer":[83],"requires":[84],"(1)":[85],"fine-grained":[86],"awareness":[88],"short":[91,114],"segment":[92],"(~128":[93],"tokens)":[94],"(4K-32K":[100],"tokens),":[101],"and":[102,106,150,153,159],"(2)":[103],"integration":[105],"reasoning":[107],"of":[108,132],"two":[111],"or":[112],"more":[113],"segments.":[115],"Through":[116],"applying":[117],"Mistral-7B,":[122],"we":[123,138],"present":[124],"FILM-7B":[125,133,167,184],"(FILl-in-the-Middle).":[126],"To":[127],"thoroughly":[128],"assess":[129],"ability":[131],"for":[134],"utilizing":[135],"contexts,":[137],"design":[139],"three":[140],"probing":[141,163,182],"tasks":[142,192,206],"encompass":[144],"various":[145],"styles":[147],"(document,":[148],"code,":[149],"structured-data":[151],"context)":[152],"retrieval":[155],"patterns":[156],"(forward,":[157],"backward,":[158],"bi-directional":[160],"retrieval).":[161],"The":[162],"results":[164],"demonstrate":[165],"robustly":[169],"retrieve":[170],"different":[173],"positions":[174],"its":[176],"32K":[177],"window.":[179],"Beyond":[180],"these":[181],"tasks,":[183],"significantly":[185],"improves":[186],"performance":[188,203],"real-world":[190],"(e.g.,":[193,207],"23.5->26.9":[194],"F1":[195],"score":[196],"NarrativeQA),":[198],"while":[199],"maintaining":[200],"comparable":[202],"short-context":[205],"59.3->59.2":[208],"accuracy":[209],"MMLU).":[211],"Github":[212],"Link:":[213],"https://github.com/microsoft/FILM.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":32},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-21T09:56:26.102985","created_date":"2025-11-03T00:00:00"}