{"id":"https://openalex.org/W7165669589","doi":"https://doi.org/10.48550/arxiv.2606.21097","title":"GRAG: Generic Response-Augmented Generation Framework for Personalized Conversational Systems","display_name":"GRAG: Generic Response-Augmented Generation Framework for Personalized Conversational Systems","publication_year":2026,"publication_date":"2026-06-19","ids":{"openalex":"https://openalex.org/W7165669589","doi":"https://doi.org/10.48550/arxiv.2606.21097"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.21097","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.21097","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":null,"license_id":null,"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.2606.21097","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139168923","display_name":"Junfeng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Junfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055365897","display_name":"Christopher T. Symons","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Symons, Christopher T.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065410886","display_name":"Ranga Raju Vatsavai","orcid":"https://orcid.org/0000-0002-7083-0267"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vatsavai, Ranga Raju","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":0.22509999573230743,"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":0.22509999573230743,"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/T12128","display_name":"AI in Service Interactions","score":0.14579999446868896,"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/T11519","display_name":"Digital Mental Health Interventions","score":0.11029999703168869,"subfield":{"id":"https://openalex.org/subfields/3202","display_name":"Applied Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.8378000259399414},{"id":"https://openalex.org/keywords/persona","display_name":"Persona","score":0.6438999772071838},{"id":"https://openalex.org/keywords/blueprint","display_name":"Blueprint","score":0.6139000058174133},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5924000144004822},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4706999957561493},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.438400000333786},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.41769999265670776},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.40549999475479126},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.398499995470047}],"concepts":[{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.8378000259399414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.800599992275238},{"id":"https://openalex.org/C313442","wikidata":"https://www.wikidata.org/wiki/Q778556","display_name":"Persona","level":2,"score":0.6438999772071838},{"id":"https://openalex.org/C155911762","wikidata":"https://www.wikidata.org/wiki/Q422321","display_name":"Blueprint","level":2,"score":0.6139000058174133},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5924000144004822},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5188000202178955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4966999888420105},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4706999957561493},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.438400000333786},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.40549999475479126},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.398499995470047},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C44210515","wikidata":"https://www.wikidata.org/wiki/Q16968978","display_name":"Bespoke","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.33739998936653137},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33500000834465027},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2913999855518341},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.26030001044273376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.21097","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.21097","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.21097","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.21097","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":null,"license_id":null,"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":{"Deploying":[0],"highly":[1],"capable":[2],"personalized":[3,224],"conversational":[4,91,162,181,225],"agents":[5],"in":[6,20,57,82,89,136,168,208,212,227],"resource-constrained":[7],"or":[8,78,93],"privacy-sensitive":[9],"environments":[10],"remains":[11],"a":[12,17,32,58,122,218],"significant":[13,64],"challenge.":[14],"We":[15,164],"identify":[16],"fundamental":[18],"bottleneck":[19],"the":[21,90,101,129,141,148,161,166],"existing":[22],"approaches:":[23],"current":[24],"training":[25],"paradigms":[26],"treat":[27],"personalization":[28,186],"and":[29,52,66,124,171,175,210],"grounding":[30,71,143],"as":[31,121],"single":[33],"monolithic":[34],"learning":[35],"problem.":[36],"Under":[37],"these":[38,109],"paradigms,":[39],"language":[40],"models":[41,134],"are":[42,85],"forced":[43],"to":[44,48,54,127,150,160,205],"simultaneously":[45],"address":[46],"what":[47],"say":[49,55],"(content":[50],"grounding)":[51],"how":[53],"it":[56],"user-specific":[59],"way":[60],"(personalization),":[61],"which":[62],"introduces":[63],"computational":[65],"optimization":[67],"challenges.":[68],"Consequently,":[69],"contextual":[70],"is":[72],"often":[73],"sacrificed":[74],"for":[75,221],"persona":[76,154],"adherence,":[77],"vice":[79],"versa,":[80],"resulting":[81],"responses":[83,116],"that":[84,107,183,191,197],"either":[86],"weakly":[87],"grounded":[88],"history":[92],"insufficiently":[94],"personalized.":[95],"In":[96],"this":[97],"work,":[98],"we":[99],"propose":[100],"Generic":[102],"Response-Augmented":[103],"Generation":[104],"(GRAG)":[105],"framework":[106],"decouples":[108],"competing":[110],"objectives":[111],"by":[112],"leveraging":[113],"offline,":[114],"generic":[115],"from":[117,144],"high-capacity,":[118],"general-purpose":[119],"LLMs":[120],"semantic":[123],"structural":[125],"scaffold":[126],"guide":[128],"fine-tuning":[130],"of":[131],"smaller,":[132],"task-specialized":[133],"seamlessly":[135],"resource-limited":[137,228],"environments.":[138,229],"By":[139],"decoupling":[140],"content":[142],"personalization,":[145],"GRAG":[146,167,192,216],"allows":[147],"model":[149],"focus":[151],"exclusively":[152],"on":[153,178],"injection":[155],"while":[156],"remaining":[157],"firmly":[158],"anchored":[159],"context.":[163],"instantiate":[165],"two":[169],"post-":[170],"pre-fusion-based":[172],"architectural":[173],"variants":[174],"evaluate":[176],"them":[177],"multiple":[179],"benchmark":[180],"datasets":[182],"cover":[184],"diverse":[185],"structures.":[187],"Our":[188],"results":[189],"demonstrate":[190],"significantly":[193],"outperforms":[194],"state-of-the-art":[195],"methods":[196],"do":[198],"not":[199],"use":[200],"auxiliary":[201],"scaffolding,":[202],"yielding":[203],"up":[204],"47%":[206],"improvements":[207],"ROUGE-2":[209],"36%":[211],"BLEU":[213],"scores.":[214],"Ultimately,":[215],"offers":[217],"generalizable":[219],"blueprint":[220],"building":[222],"grounding-aware":[223],"systems":[226]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-24T00:00:00"}