{"id":"https://openalex.org/W7166807244","doi":"https://doi.org/10.2139/ssrn.7247158","title":"Long-document Representation for Retrieval and Retrieval-augmented Generation: A Representation-First, Distillation-aware Survey","display_name":"Long-document Representation for Retrieval and Retrieval-augmented Generation: A Representation-First, Distillation-aware Survey","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166807244","doi":"https://doi.org/10.2139/ssrn.7247158"},"language":"en","primary_location":{"id":"doi:10.2139/ssrn.7247158","doi":"https://doi.org/10.2139/ssrn.7247158","is_oa":true,"landing_page_url":"https://doi.org/10.2139/ssrn.7247158","pdf_url":null,"source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"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":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.2139/ssrn.7247158","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070018836","display_name":"Roberto Mart\u00ednez-Cruz","orcid":"https://orcid.org/0009-0009-4264-1678","observed_orcids":["https://orcid.org/0009-0009-4264-1678"]},"institutions":[{"id":"https://openalex.org/I4405267806","display_name":"Instituto de Investigaci\u00f3n Tecnol\u00f3gica","ror":"https://ror.org/04fc53857","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4405267806","https://openalex.org/I96580804"]},{"id":"https://openalex.org/I96580804","display_name":"Universidad Pontificia Comillas","ror":"https://ror.org/017mdc710","country_code":"ES","type":"education","lineage":["https://openalex.org/I96580804"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Roberto Martinez-Cruz","raw_affiliation_strings":["Comillas Pontifical University - Institute for Research in Technology (IIT), Madrid, Spain","DD-AIM, New York, NY, United States"],"raw_orcid":"https://orcid.org/0009-0009-4264-1678","affiliations":[{"raw_affiliation_string":"Comillas Pontifical University - Institute for Research in Technology (IIT), Madrid, Spain","institution_ids":["https://openalex.org/I4405267806","https://openalex.org/I96580804"]},{"raw_affiliation_string":"DD-AIM, New York, NY, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006896554","display_name":"\u00c1lvaro J. L\u00f3pez-L\u00f3pez","orcid":"https://orcid.org/0000-0001-9879-5603","observed_orcids":["https://orcid.org/0000-0001-9879-5603"]},"institutions":[{"id":"https://openalex.org/I4405267806","display_name":"Instituto de Investigaci\u00f3n Tecnol\u00f3gica","ror":"https://ror.org/04fc53857","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4405267806","https://openalex.org/I96580804"]},{"id":"https://openalex.org/I96580804","display_name":"Universidad Pontificia Comillas","ror":"https://ror.org/017mdc710","country_code":"ES","type":"education","lineage":["https://openalex.org/I96580804"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"\u00c1lvaro Jes\u00fas L\u00f3pez-L\u00f3pez","raw_affiliation_strings":["Comillas Pontifical University - Institute for Research in Technology (IIT)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Comillas Pontifical University - Institute for Research in Technology (IIT)","institution_ids":["https://openalex.org/I4405267806","https://openalex.org/I96580804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022728953","display_name":"Jos\u00e9 Portela","orcid":"https://orcid.org/0000-0002-7839-8982","observed_orcids":["https://orcid.org/0000-0002-7839-8982"]},"institutions":[{"id":"https://openalex.org/I96580804","display_name":"Universidad Pontificia Comillas","ror":"https://ror.org/017mdc710","country_code":"ES","type":"education","lineage":["https://openalex.org/I96580804"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jose Portela","raw_affiliation_strings":["Comillas Pontifical University, Alberto Aguilera 21, Madrid, 28015, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Comillas Pontifical University, Alberto Aguilera 21, Madrid, 28015, Spain","institution_ids":["https://openalex.org/I96580804"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5146973200","display_name":"Alex Zayat","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Zayat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070018836"],"corresponding_institution_ids":["https://openalex.org/I4405267806","https://openalex.org/I96580804"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9175000190734863,"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":0.9175000190734863,"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":0.07699999958276749,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0010999999940395355,"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/document-embeddings","display_name":"document embeddings","score":0.6150000095367432},{"id":"https://openalex.org/keywords/long-document-retrieval","display_name":"long document retrieval","score":0.7269999980926514},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9990000128746033},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.9350000023841858},{"id":"https://openalex.org/keywords/chunking","display_name":"chunking","score":0.5130000114440918},{"id":"https://openalex.org/keywords/hierarchical-representation","display_name":"hierarchical representation","score":0.7730000019073486},{"id":"https://openalex.org/keywords/graph-representation","display_name":"graph representation","score":0.6899999976158142},{"id":"https://openalex.org/keywords/evidence-retrieval","display_name":"evidence retrieval","score":0.34299999475479126},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.5799999833106995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7254999876022339},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6161999702453613},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.582099974155426},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5267000198364258},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.525600016117096},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45410001277923584},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4049000144004822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3921000063419342},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3262999951839447},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3181999921798706},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.2139/ssrn.7247158","doi":"https://doi.org/10.2139/ssrn.7247158","is_oa":true,"landing_page_url":"https://doi.org/10.2139/ssrn.7247158","pdf_url":null,"source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"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":"posted-content"},{"id":"doi:10.5281/zenodo.21104446","doi":"https://doi.org/10.5281/zenodo.21104446","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21104446","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.21104447","doi":"https://doi.org/10.5281/zenodo.21104447","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21104447","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.2139/ssrn.7247158","doi":"https://doi.org/10.2139/ssrn.7247158","is_oa":true,"landing_page_url":"https://doi.org/10.2139/ssrn.7247158","pdf_url":null,"source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"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":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W2250539671","https://openalex.org/W2612431505","https://openalex.org/W2612953412","https://openalex.org/W2779681640","https://openalex.org/W2889787757","https://openalex.org/W2912924812","https://openalex.org/W2963341956","https://openalex.org/W2964110616","https://openalex.org/W2964165804","https://openalex.org/W2971569798","https://openalex.org/W2997517014","https://openalex.org/W3015883388","https://openalex.org/W3016913119","https://openalex.org/W3017604292","https://openalex.org/W3034368386","https://openalex.org/W3034457371","https://openalex.org/W3035102548","https://openalex.org/W3038033387","https://openalex.org/W3085139254","https://openalex.org/W3105238007","https://openalex.org/W3156636935","https://openalex.org/W4385570167","https://openalex.org/W4385573804","https://openalex.org/W4385573970","https://openalex.org/W4386488973","https://openalex.org/W4389520322","https://openalex.org/W4389523965","https://openalex.org/W4389524502","https://openalex.org/W4389921502","https://openalex.org/W4392384310","https://openalex.org/W4393160872","https://openalex.org/W4401857375","https://openalex.org/W4402670999","https://openalex.org/W4402671753","https://openalex.org/W4402671766","https://openalex.org/W4402672004","https://openalex.org/W4404212170","https://openalex.org/W4404781754","https://openalex.org/W4404782504","https://openalex.org/W4404783687","https://openalex.org/W4410247559","https://openalex.org/W4412886690","https://openalex.org/W4412886823","https://openalex.org/W4412889839","https://openalex.org/W4412945302","https://openalex.org/W4415796011","https://openalex.org/W4415797504","https://openalex.org/W4416036914","https://openalex.org/W4416037009","https://openalex.org/W4416037429","https://openalex.org/W7108331775","https://openalex.org/W7133214597","https://openalex.org/W7138012369","https://openalex.org/W7157969354"],"related_works":["https://openalex.org/W7128810349","https://openalex.org/W7213230773","https://openalex.org/W7080713867","https://openalex.org/W7161277215","https://openalex.org/W7165129584","https://openalex.org/W4417300129","https://openalex.org/W4412378305","https://openalex.org/W4417101535","https://openalex.org/W4412888941","https://openalex.org/W4389524594"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-07-02T00:00:00"}