{"id":"https://openalex.org/W4416034133","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.949","title":"Understanding and Improving Information Preservation in Prompt Compression for LLMs","display_name":"Understanding and Improving Information Preservation in Prompt Compression for LLMs","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034133","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.949"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.949","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.949","pdf_url":"https://aclanthology.org/2025.findings-emnlp.949.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.949.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120308498","display_name":"Weronika \u0141ajewska","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weronika \u0141ajewska","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076120409","display_name":"Momchil Hardalov","orcid":"https://orcid.org/0000-0001-8095-3570"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Momchil Hardalov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004059222","display_name":"Laura Aina","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laura Aina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010761363","display_name":"Neha Anna John","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Neha Anna John","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109299108","display_name":"Hang Su","orcid":"https://orcid.org/0009-0003-6834-0087"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hang Su","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103372090","display_name":"Llu\u0131\u0301s M\u00e0rquez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lluis Marquez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1081,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84430728,"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":"17520","last_page":"17541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.131400004029274,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.131400004029274,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.11869999766349792,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.06199999898672104,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.4296000003814697},{"id":"https://openalex.org/keywords/complete-information","display_name":"Complete information","score":0.28110000491142273},{"id":"https://openalex.org/keywords/information-system","display_name":"Information system","score":0.2782999873161316},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2766999900341034},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.26080000400543213}],"concepts":[{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.5138999819755554},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42649999260902405},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.34389999508857727},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.3077999949455261},{"id":"https://openalex.org/C77595967","wikidata":"https://www.wikidata.org/wiki/Q3151013","display_name":"Forensic engineering","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2989000082015991},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2603999972343445}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.949","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.949","pdf_url":"https://aclanthology.org/2025.findings-emnlp.949.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.949","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.949","pdf_url":"https://aclanthology.org/2025.findings-emnlp.949.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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034133.pdf","grobid_xml":"https://content.openalex.org/works/W4416034133.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,18,88,144,150,157],"large":[3],"language":[4],"models":[5],"(LLMs)":[6],"have":[7,46],"enabled":[8],"their":[9],"successful":[10],"application":[11],"to":[12,28,49,111,130,142],"a":[13,61],"broad":[14],"range":[15],"of":[16,70],"tasks.However,":[17],"information-intensive":[19],"tasks,":[20],"the":[21,51,89,116,162],"prompt":[22,43,71],"length":[23,56],"can":[24],"grow":[25],"fast,":[26],"leading":[27],"increased":[29],"computational":[30],"requirements,":[31],"performance":[32,120],"degradation,":[33],"and":[34,57,92,102,106,152],"induced":[35],"biases":[36],"from":[37,115],"irrelevant":[38],"or":[39],"redundant":[40],"information.Recently,":[41],"various":[42],"compression":[44,72,80,104,138],"techniques":[45],"been":[47],"introduced":[48],"optimize":[50],"trade-off":[52,166],"between":[53],"reducing":[54],"input":[55,90],"retaining":[58],"performance.We":[59],"propose":[60],"holistic":[62],"evaluation":[63],"framework":[64],"that":[65,108,161],"allows":[66],"for":[67],"in-depth":[68],"analysis":[69],"methods.We":[73],"focus":[74],"on":[75,121],"three":[76],"key":[77,113],"aspects,":[78],"besides":[79],"ratio:":[81],"(i)":[82],"downstream":[83,145],"task":[84],"performance,":[85,146],"(ii)":[86],"grounding":[87],"context,":[91],"(iii)":[93],"information":[94],"preservation.Using":[95],"our":[96],"framework,":[97],"we":[98,127,159],"analyze":[99],"state-of-the-art":[100],"soft":[101,133,170],"hard":[103],"methods":[105],"show":[107],"some":[109],"fail":[110],"preserve":[112],"details":[114],"original":[117],"prompt,":[118],"limiting":[119],"complex":[122],"tasks.By":[123],"identifying":[124],"these":[125],"limitations,":[126],"are":[128],"able":[129],"improve":[131],"one":[132],"prompting":[134,171],"method":[135],"by":[136],"controlling":[137],"granularity,":[139],"achieving":[140],"up":[141],"+23%":[143],"+8":[147],"BERTScore":[148],"points":[149],"grounding,":[151],"2.7":[153],"more":[154],"entities":[155],"preserved":[156],"compression.Ultimately,":[158],"find":[160],"best":[163],"effectiveness/compression":[164],"rate":[165],"is":[167],"achieved":[168],"with":[169,173],"combined":[172],"sequence-level":[174],"training.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}