{"id":"https://openalex.org/W4416034185","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.878","title":"Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation","display_name":"Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034185","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.878"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.878","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.878","pdf_url":"https://aclanthology.org/2025.findings-emnlp.878.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.878.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035587454","display_name":"Dongwon Jung","orcid":"https://orcid.org/0000-0002-2771-9408"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongwon Jung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432497","display_name":"Qin Liu","orcid":"https://orcid.org/0000-0002-5465-1189"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004915056","display_name":"Tenghao Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tenghao Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067460538","display_name":"Ben Zhou","orcid":"https://orcid.org/0000-0001-7177-2882"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102861481","display_name":"Muhao Chen","orcid":"https://orcid.org/0000-0003-0118-3147"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muhao 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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2960751,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16181","last_page":"16196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.1817999929189682,"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":0.1817999929189682,"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":0.16419999301433563,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.10080000013113022,"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/compression","display_name":"Compression (physics)","score":0.5033000111579895},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.2554999887943268},{"id":"https://openalex.org/keywords/deformation","display_name":"Deformation (meteorology)","score":0.24860000610351562},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.2362000048160553},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.22110000252723694}],"concepts":[{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5033000111579895},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4000000059604645},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C204366326","wikidata":"https://www.wikidata.org/wiki/Q3027650","display_name":"Deformation (meteorology)","level":2,"score":0.24860000610351562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24379999935626984},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.2371000051498413},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2362000048160553},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2337999939918518},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.22110000252723694},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.20260000228881836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.878","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.878","pdf_url":"https://aclanthology.org/2025.findings-emnlp.878.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.878","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.878","pdf_url":"https://aclanthology.org/2025.findings-emnlp.878.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1795802330","display_name":"CICI: UCSS: Enabling a Safe and Directive Multi-modal Foundation Model Ecosystem for Food Science Research","funder_award_id":"2531126","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4706632707","display_name":"Proto-OKN Theme 1: Knowledge Graph Construction for Resilient, Trustworthy, and Secure Software Supply Chains","funder_award_id":"2333736","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6584218474","display_name":null,"funder_award_id":"HR00112490370","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034185.pdf","grobid_xml":"https://content.openalex.org/works/W4416034185.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"improves":[3],"large":[4],"language":[5],"models":[6],"(LMs)":[7],"by":[8,126],"incorporating":[9],"non-parametric":[10,144],"knowledge":[11,103,145],"through":[12],"evidence":[13,39,46,58,76,86,92,116,147],"retrieved":[14,45,91],"from":[15,33,104],"external":[16],"sources.However,":[17],"it":[18],"often":[19],"struggles":[20],"to":[21,52,63,73,95,128],"cope":[22],"with":[23,47],"inconsistent":[24],"and":[25,143],"irrelevant":[26],"information":[27],"that":[28,89,109],"can":[29],"distract":[30],"the":[31,44,56,64,75,96,105,113,137],"LM":[32],"its":[34],"tasks,":[35,70],"especially":[36],"when":[37],"multiple":[38,120],"pieces":[40],"are":[41],"required.While":[42],"compressing":[43],"a":[48,83],"compression":[49,87,117,133],"model":[50,66],"aims":[51],"address":[53],"this":[54],"issue,":[55],"compressed":[57],"may":[59],"still":[60],"be":[61],"unfamiliar":[62],"target":[65,97],"used":[67],"for":[68],"downstream":[69],"potentially":[71],"failing":[72],"utilize":[74],"effectively.We":[77],"propose":[78],"FAVICOMP":[79,110],"(FAmiliarity-aware":[80],"EVIdence":[81],"COMPression),":[82],"novel":[84],"inference-time":[85],"technique":[88],"makes":[90],"more":[93],"familiar":[94],"model,":[98],"while":[99,130],"seamlessly":[100],"integrating":[101],"parametric":[102,142],"model.Experimental":[106],"results":[107],"show":[108],"consistently":[111],"outperforms":[112],"most":[114],"recent":[115],"baselines":[118],"across":[119],"open-domain":[121],"QA":[122],"datasets,":[123],"improving":[124],"accuracy":[125],"up":[127],"28.1%":[129],"achieving":[131],"high":[132],"rates.Additionally,":[134],"we":[135],"demonstrate":[136],"effective":[138],"integration":[139],"of":[140],"both":[141],"during":[146],"compression.":[148],"1":[149]},"counts_by_year":[],"updated_date":"2026-08-03T07:22:36.454288","created_date":"2025-11-08T00:00:00"}