{"id":"https://openalex.org/W7157148718","doi":"https://doi.org/10.48550/arxiv.2604.23277","title":"From Similarity to Structure: Training-free LLM Context Compression with Hybrid Graph Priors","display_name":"From Similarity to Structure: Training-free LLM Context Compression with Hybrid Graph Priors","publication_year":2026,"publication_date":"2026-04-25","ids":{"openalex":"https://openalex.org/W7157148718","doi":"https://doi.org/10.48550/arxiv.2604.23277"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.23277","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23277","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.23277","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133156570","display_name":"Yitian Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yitian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134819568","display_name":"Chaoning Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chaoning","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134810110","display_name":"Jiaquan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jiaquan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134781215","display_name":"Zhenzhen Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Zhenzhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134808669","display_name":"Jinyu Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Jinyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134807169","display_name":"Sung-Ho Bae","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bae, Sung-Ho","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081811548","display_name":"Lik\u2010Hang Lee","orcid":"https://orcid.org/0000-0003-1361-1612"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Lik-Hang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134807971","display_name":"Caiyan Qin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Caiyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134815896","display_name":"Yang Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yang","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":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/T10181","display_name":"Natural Language Processing Techniques","score":0.28619998693466187,"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":0.28619998693466187,"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":0.2612000107765198,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.09210000187158585,"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/redundancy","display_name":"Redundancy (engineering)","score":0.6557999849319458},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4607999920845032},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42800000309944153},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.42579999566078186},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.41620001196861267},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.39730000495910645},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.3813000023365021},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37940001487731934},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.3643999993801117},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.3546999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7394000291824341},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6557999849319458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.59170001745224},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4607999920845032},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42800000309944153},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.42579999566078186},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.39730000495910645},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3549000024795532},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3463999927043915},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34599998593330383},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.31290000677108765},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2680000066757202},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.26759999990463257},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2583000063896179},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.2558000087738037},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.23277","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23277","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.23277","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23277","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Long-context":[0],"large":[1],"language":[2],"models":[3],"remain":[4],"computationally":[5],"expensive":[6],"to":[7,12,46],"run":[8],"and":[9,42,53,68,108,123,158],"often":[10,44],"fail":[11],"reliably":[13],"process":[14],"very":[15],"long":[16],"inputs,":[17],"which":[18],"makes":[19],"context":[20,140],"compression":[21,29,70],"an":[22,112],"important":[23],"component":[24],"of":[25,77],"many":[26],"systems.":[27],"Existing":[28],"approaches":[30],"typically":[31],"rely":[32],"on":[33,146,164],"trained":[34],"compressors,":[35],"dense":[36],"retrieval-style":[37],"selection,":[38],"or":[39],"heuristic":[40],"trimming,":[41],"they":[43],"struggle":[45],"jointly":[47],"preserve":[48],"task":[49,117],"relevance,":[50,118],"topic":[51,104],"coverage,":[52],"cross-sentence":[54],"coherence":[55],"under":[56],"a":[57,66,74,87,103,124,137],"strict":[58],"token":[59],"budget.":[60],"To":[61],"address":[62],"this,":[63],"we":[64],"propose":[65],"training-free":[67],"model-agnostic":[69],"framework":[71],"that":[72,92,115,150],"selects":[73],"compact":[75],"set":[76],"sentences":[78,110],"guided":[79],"by":[80],"structural":[81],"graph":[82,91],"priors.":[83],"Our":[84],"method":[85],"constructs":[86],"sparse":[88],"hybrid":[89],"sentence":[90],"combines":[93],"mutual":[94],"k-NN":[95],"semantic":[96],"edges":[97],"with":[98,132,155],"short-range":[99],"sequential":[100],"edges,":[101],"extracts":[102],"skeleton":[105],"via":[106],"clustering,":[107],"ranks":[109],"using":[111],"interpretable":[113],"score":[114],"integrates":[116],"cluster":[119],"representativeness,":[120],"bridge":[121],"centrality,":[122],"cycle":[125],"coverage":[126],"cue.":[127],"A":[128],"budgeted":[129],"greedy":[130],"selection":[131],"redundancy":[133],"suppression":[134],"then":[135],"produces":[136],"readable":[138],"compressed":[139],"in":[141],"original":[142],"order.":[143],"Experimental":[144],"results":[145],"four":[147],"datasets":[148],"show":[149],"our":[151],"approach":[152],"is":[153],"competitive":[154],"strong":[156],"extractive":[157],"abstractive":[159],"baselines,":[160],"demonstrating":[161],"larger":[162],"gains":[163],"long-document":[165],"benchmarks.":[166]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-29T00:00:00"}