{"id":"https://openalex.org/W7161021981","doi":"https://doi.org/10.48550/arxiv.2605.11662","title":"HSUGA: LLM-Enhanced Recommendation with Hierarchical Semantic Understanding and Group-Aware Alignment","display_name":"HSUGA: LLM-Enhanced Recommendation with Hierarchical Semantic Understanding and Group-Aware Alignment","publication_year":2026,"publication_date":"2026-05-12","ids":{"openalex":"https://openalex.org/W7161021981","doi":"https://doi.org/10.48550/arxiv.2605.11662"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.11662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11662","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2605.11662","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121238029","display_name":"Guorui Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Guorui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136018225","display_name":"Dugang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Dugang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136034232","display_name":"Lei Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136054058","display_name":"Xing Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Xing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136028142","display_name":"Zhong Ming","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming, Zhong","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/T10203","display_name":"Recommender Systems and Techniques","score":0.5397999882698059,"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"}},"topics":[{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.5397999882698059,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.09000000357627869,"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":0.06109999865293503,"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/embedding","display_name":"Embedding","score":0.5817000269889832},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5325999855995178},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43650001287460327},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.43549999594688416},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.3456999957561493},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.3391999900341034},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.3165999948978424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8317999839782715},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5817000269889832},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5325999855995178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4740999937057495},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.43549999594688416},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3953000009059906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3578999936580658},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31690001487731934},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2921999990940094},{"id":"https://openalex.org/C166423231","wikidata":"https://www.wikidata.org/wiki/Q1891170","display_name":"Semantic search","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.11662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11662","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2605.11662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11662","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":{"Large":[0],"language":[1],"model":[2],"(LLM)-enhanced":[3],"sequential":[4],"recommendation":[5],"typically":[6],"aims":[7],"to":[8,56,88],"improve":[9],"two":[10,26,109],"core":[11,110],"components:":[12,111],"user":[13,60,84,140,152],"semantic":[14,72,141,148],"embedding":[15,73],"extraction":[16,31],"and":[17,116,127,161,180],"utilization.":[18],"Despite":[19],"promising":[20],"results,":[21],"existing":[22],"methods":[23,34,68],"still":[24],"have":[25],"limitations:":[27],"1)":[28],"In":[29,63],"the":[30,64,70,80,108,137,145,178],"stage,":[32,66],"most":[33,67],"directly":[35],"input":[36],"long":[37,48],"interaction":[38],"sequence":[39],"fragments":[40],"into":[41],"LLM":[42],"for":[43,76,105,158,164],"preference":[44,125,129],"summarization.":[45],"However,":[46],"excessively":[47],"sequences":[49],"increase":[50],"inference":[51],"difficulty,":[52],"making":[53],"it":[54],"challenging":[55],"reliably":[57],"infer":[58],"accurate":[59],"embeddings.":[61],"2)":[62],"utilization":[65,74,149],"employ":[69],"same":[71],"strategy":[75],"all":[77],"users,":[78],"neglecting":[79],"differences":[81],"caused":[82],"by":[83],"activity":[85,153],"levels,":[86,154],"leading":[87],"suboptimal":[89],"performance.":[90],"To":[91],"address":[92],"these":[93],"issues,":[94],"we":[95],"propose":[96],"HSUGA,":[97],"which":[98],"introduces":[99],"a":[100,122],"simple":[101],"yet":[102],"effective":[103],"plugin":[104],"each":[106],"of":[107,139,147,182],"Hierarchical":[112],"Semantic":[113],"Understanding":[114],"(HSU)":[115],"Group-Aware":[117],"Alignment":[118],"(GAA).":[119],"HSU":[120],"performs":[121],"staged":[123],"two-phase":[124],"mining":[126],"models":[128],"evolution":[130],"through":[131],"constrained":[132],"editing":[133],"operations,":[134],"thereby":[135],"improving":[136],"reliability":[138],"extraction.":[142],"GAA":[143],"adjusts":[144],"intensity":[146],"based":[150],"on":[151,173],"providing":[155],"weaker":[156],"alignment":[157],"active":[159],"users":[160,165],"stronger":[162],"guidance":[163],"with":[166],"sparse":[167],"historical":[168],"data.":[169],"Finally,":[170],"extensive":[171],"experiments":[172],"three":[174],"benchmark":[175],"datasets":[176],"demonstrate":[177],"effectiveness":[179],"compatibility":[181],"HSUGA.":[183]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-14T00:00:00"}