{"id":"https://openalex.org/W4412378305","doi":"https://doi.org/10.1145/3726302.3731690","title":"Long Context vs. RAG: Strategies for Processing Long Documents in LLMs","display_name":"Long Context vs. RAG: Strategies for Processing Long Documents in LLMs","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412378305","doi":"https://doi.org/10.1145/3726302.3731690"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3731690","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3731690","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3731690","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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3731690","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xinze Li","orcid":"https://orcid.org/0009-0000-5144-3766"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xinze Li","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0000-5144-3766","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113613553","display_name":"Y. Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I2802444338","display_name":"King Center","ror":"https://ror.org/03nxex423","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2802444338"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yushi Bai","raw_affiliation_strings":["Tsinghua University, Beijing, USA"],"raw_orcid":"https://orcid.org/0009-0009-7611-1093","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, USA","institution_ids":["https://openalex.org/I2802444338"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025877787","display_name":"Bowen Jin","orcid":"https://orcid.org/0000-0003-1295-2829"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bowen Jin","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, USA"],"raw_orcid":"https://orcid.org/0000-0003-1295-2829","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029052244","display_name":"Fengbin Zhu","orcid":"https://orcid.org/0000-0001-6776-2040"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Fengbin Zhu","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6776-2040","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027533517","display_name":"Liangming Pan","orcid":"https://orcid.org/0000-0002-7789-7739"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liangming Pan","raw_affiliation_strings":["University of Arizona, Tucson, USA"],"raw_orcid":"https://orcid.org/0000-0002-7789-7739","affiliations":[{"raw_affiliation_string":"University of Arizona, Tucson, USA","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023326846","display_name":"Yixin Cao","orcid":"https://orcid.org/0000-0001-7157-6961"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixin Cao","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7157-6961","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.4249,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.97862561,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4110","last_page":"4113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9922999739646912,"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":0.9922999739646912,"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":0.9909999966621399,"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":0.9764999747276306,"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":0.6409635543823242},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5863440632820129},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.21765941381454468}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6409635543823242},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5863440632820129},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.21765941381454468},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3731690","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3731690","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3731690","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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3726302.3731690","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3731690","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3731690","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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412378305.pdf","grobid_xml":"https://content.openalex.org/works/W4412378305.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2912817604","https://openalex.org/W2912924812","https://openalex.org/W2963961878","https://openalex.org/W2964110616","https://openalex.org/W3121694563","https://openalex.org/W3155807546","https://openalex.org/W3209632425","https://openalex.org/W4213009331","https://openalex.org/W4252076394","https://openalex.org/W4309674289","https://openalex.org/W4382603041","https://openalex.org/W4389519118","https://openalex.org/W4389984066","https://openalex.org/W4392930030","https://openalex.org/W4400529052","https://openalex.org/W4401023643","https://openalex.org/W4402670549","https://openalex.org/W4402671152","https://openalex.org/W4402671766","https://openalex.org/W4402955078","https://openalex.org/W4403344273","https://openalex.org/W4404354805","https://openalex.org/W4405655804"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"excel":[4],"at":[5],"zero-":[6],"and":[7,46,80,91,98,110,122,136,143],"few-shot":[8],"learning":[9],"but":[10],"are":[11],"restricted":[12],"by":[13],"the":[14,87],"length":[15],"of":[16,112,118],"context":[17],"windows":[18],"when":[19],"processing":[20,149],"long":[21,150],"documents.":[22],"Two":[23],"strategies":[24],"have":[25],"emerged":[26],"to":[27,42,69,106],"overcome":[28],"this":[29],"limitation:":[30],"(1)":[31],"Long":[32],"Context":[33],"(LC)":[34],"methods,":[35],"which":[36,51],"extend":[37],"or":[38,58],"compress":[39],"transformer":[40,75],"architectures":[41],"input":[43],"more":[44],"text;":[45],"(2)":[47],"Retrieval-Augmented":[48],"Generation":[49],"(RAG),":[50],"integrates":[52],"external":[53],"knowledge":[54],"sources":[55],"via":[56],"embedding-":[57],"index-based":[59],"retrieval.":[60],"This":[61],"half-day":[62],"tutorial":[63],"offers":[64],"a":[65],"unified,":[66],"beginner-friendly":[67],"introduction":[68],"both":[70],"approaches.":[71],"We":[72,100,125],"first":[73],"review":[74],"fundamentals-positional":[76],"encoding,":[77],"attention":[78],"complexity,":[79],"common":[81],"LC":[82,113],"techniques.":[83],"Next,":[84],"we":[85],"explain":[86],"classic":[88],"RAG":[89,93,115],"pipeline":[90],"recent":[92,103],"strategies,":[94],"alongside":[95],"evaluation":[96],"metrics":[97],"benchmarks.":[99],"also":[101],"analyze":[102],"empirical":[104],"studies":[105],"highlight":[107],"strengths,":[108],"limitations,":[109],"trade-offs":[111],"vs.":[114],"in":[116,152],"terms":[117],"scalability,":[119],"computational":[120],"cost,":[121],"retrieval":[123],"effectiveness.":[124],"conclude":[126],"with":[127,145],"best":[128],"practices":[129],"for":[130,148],"real-world":[131],"deployments,":[132],"emerging":[133],"hybrid":[134],"architectures,":[135],"open":[137],"research":[138],"directions,":[139],"equipping":[140],"IR":[141],"researchers":[142],"practitioners":[144],"actionable":[146],"guidelines":[147],"documents":[151],"LLMs.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}