{"id":"https://openalex.org/W7164380022","doi":"https://doi.org/10.48550/arxiv.2606.12411","title":"Context-Driven Incremental Compression for Multi-Turn Dialogue Generation","display_name":"Context-Driven Incremental Compression for Multi-Turn Dialogue Generation","publication_year":2026,"publication_date":"2026-06-10","ids":{"openalex":"https://openalex.org/W7164380022","doi":"https://doi.org/10.48550/arxiv.2606.12411"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.12411","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.12411","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.2606.12411","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108307830","display_name":"Yeongseo Jung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jung, Yeongseo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138459673","display_name":"Jaehyeok Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Jaehyeok","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112223308","display_name":"Eunseo Jung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jung, Eunseo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138466453","display_name":"Jiachuan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jiachuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138454188","display_name":"Yongqi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yongqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138469747","display_name":"Ka Chun Cheung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheung, Ka Chun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138460268","display_name":"Simon See","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"See, Simon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138479570","display_name":"Lei Chen (54296)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Lei","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/T10028","display_name":"Topic Modeling","score":0.7829999923706055,"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":0.7829999923706055,"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/T12031","display_name":"Speech and dialogue systems","score":0.11299999803304672,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.04749999940395355,"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/perplexity","display_name":"Perplexity","score":0.6841999888420105},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6380000114440918},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5716000199317932},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5587000250816345},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5526000261306763},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5058000087738037},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4934000074863434},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.44760000705718994},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.428600013256073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363999724388123},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.6841999888420105},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6380000114440918},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5716000199317932},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5587000250816345},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5526000261306763},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5058000087738037},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4934000074863434},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.44760000705718994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.429500013589859},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.428600013256073},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4259999990463257},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38199999928474426},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.36489999294281006},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33959999680519104},{"id":"https://openalex.org/C186886427","wikidata":"https://www.wikidata.org/wiki/Q5441213","display_name":"Feedback loop","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3269999921321869},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3131999969482422},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.30790001153945923},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2897000014781952},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C106195933","wikidata":"https://www.wikidata.org/wiki/Q7847935","display_name":"Truncation (statistics)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2639000117778778},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.12411","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.12411","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.2606.12411","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.12411","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"conversational":[1,54],"agents":[2],"condition":[3],"on":[4,133],"an":[5],"ever-growing":[6],"dialogue":[7,91,135,155,163],"history":[8],"at":[9],"each":[10,94],"turn,":[11,95],"incurring":[12],"redundant":[13],"attention":[14],"and":[15,42,56,65,81,100,107,140,150],"encoding":[16],"costs":[17],"that":[18],"grow":[19],"with":[20],"conversation":[21,76],"length.":[22],"Naive":[23],"truncation":[24],"or":[25,37],"summarization":[26],"degrades":[27],"fidelity,":[28],"while":[29],"existing":[30],"context":[31,51],"compressors":[32],"lack":[33],"cross-turn":[34,126],"memory":[35],"sharing":[36],"revision,":[38],"causing":[39],"information":[40,104],"loss":[41],"compounding":[43],"errors":[44],"in":[45,87],"long":[46],"dialogues.":[47],"We":[48],"revisit":[49],"the":[50],"compression":[52,85],"under":[53],"dynamics":[55],"empirically":[57],"present":[58],"its":[59],"fragility.":[60],"To":[61],"improve":[62],"both":[63],"efficiency":[64,141],"robustness,":[66],"we":[67,116],"introduce":[68],"Context-Driven":[69],"Incremental":[70],"Compression":[71],"(C-DIC),":[72],"which":[73],"treats":[74],"a":[75,88,96,158],"as":[77],"interleaved":[78],"contextual":[79],"threads":[80],"stores":[82],"revisable":[83],"per-thread":[84],"states":[86],"single,":[89],"compact":[90],"memory.":[92],"At":[93],"lightweight":[97],"retrieve,":[98],"revise,":[99],"write-back":[101],"loop":[102],"shares":[103],"across":[105],"turns":[106],"updates":[108],"stale":[109],"memories,":[110],"stabilizing":[111],"long-horizon":[112],"behavior.":[113],"In":[114],"addition,":[115],"adapt":[117],"truncated":[118],"backpropagation-through-time":[119],"(TBPTT)":[120],"to":[121,161],"our":[122],"multi-turn":[123],"setting,":[124],"learning":[125],"dependencies":[127],"without":[128],"full-history":[129],"backpropagation.":[130],"Extensive":[131],"experiments":[132],"long-form":[134],"benchmarks":[136],"demonstrate":[137],"superior":[138],"performance":[139],"of":[142,154],"C-DIC;":[143],"notably,":[144],"C-DIC":[145],"shows":[146],"stable":[147],"inference":[148],"latency":[149],"perplexity":[151],"over":[152],"hundreds":[153],"turns,":[156],"supporting":[157],"scalable":[159],"path":[160],"high-quality":[162],"modeling.":[164]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-12T00:00:00"}