{"id":"https://openalex.org/W7165140830","doi":"https://doi.org/10.48550/arxiv.2606.18897","title":"SAERec: Constructing Fine-grained Interpretable Intents Priors via Sparse Autoencoders for Recommendation","display_name":"SAERec: Constructing Fine-grained Interpretable Intents Priors via Sparse Autoencoders for Recommendation","publication_year":2026,"publication_date":"2026-06-17","ids":{"openalex":"https://openalex.org/W7165140830","doi":"https://doi.org/10.48550/arxiv.2606.18897"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.18897","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.18897","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":"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.2606.18897","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138839544","display_name":"Jiangnan Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Jiangnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090578536","display_name":"X . Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Xuansheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138856551","display_name":"Yu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138857795","display_name":"Xin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138877813","display_name":"Ninghao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Ninghao","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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.6019999980926514,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.6019999980926514,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.21819999814033508,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.019899999722838402,"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/interpretability","display_name":"Interpretability","score":0.8282999992370605},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7078999876976013},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6204000115394592},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6198999881744385},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5730999708175659},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4823000133037567},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4699999988079071},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.46709999442100525},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.448199987411499}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8282999992370605},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7940000295639038},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7078999876976013},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6204000115394592},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6198999881744385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.583299994468689},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5730999708175659},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5026999711990356},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4823000133037567},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4699999988079071},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.46709999442100525},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.44679999351501465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43950000405311584},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.42829999327659607},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41999998688697815},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40459999442100525},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31779998540878296},{"id":"https://openalex.org/C28076734","wikidata":"https://www.wikidata.org/wiki/Q63087","display_name":"Coreference","level":3,"score":0.3138999938964844},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.3125999867916107},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.18897","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.18897","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":"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.2606.18897","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.18897","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":"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":{"Intent-based":[0],"recommender":[1,82],"systems":[2],"have":[3],"gained":[4],"significant":[5],"attention":[6,206],"for":[7,76,114,157,232],"improving":[8],"accuracy":[9],"and":[10,47,58,62,88,145,181,212,216],"interpretability":[11],"by":[12,137,221],"modeling":[13],"the":[14,43,64,73,129,228,240],"underlying":[15],"motivations":[16],"behind":[17],"user":[18,27,230],"behaviors.":[19],"Most":[20],"existing":[21],"models":[22,135],"derive":[23],"intents":[24,127,163,175,183,198],"directly":[25],"from":[26,92,128,153,164],"sequences":[28],"via":[29],"clustering":[30],"or":[31],"prototype":[32],"learning.":[33],"However,":[34],"they":[35],"are":[36],"sensitive":[37],"to":[38,55,96,143,169,195,226],"sequence":[39,200],"quality,":[40,192],"require":[41],"presetting":[42],"number":[44],"of":[45,66,124,132,242],"intents,":[46],"lack":[48],"explicit":[49],"semantic":[50],"grounding.":[51],"These":[52],"issues":[53],"lead":[54],"an":[56,222],"incomplete":[57],"coarse":[59],"intent":[60,90,115,218],"set":[61,123,166],"limit":[63],"effectiveness":[65],"recommendation.":[67,98,171,233],"In":[68],"this":[69,165],"paper,":[70],"we":[71,118,160,202],"propose":[72,203],"Sparse":[74],"Autoencoder":[75],"intent-based":[77],"recommendation":[78],"(SAERec),":[79],"a":[80,86,93,121,139,177,204],"novel":[81],"that":[83,208],"automatically":[84],"constructs":[85],"fine-grained":[87,125],"interpretable":[89,126],"space":[91,131],"textual":[94,154],"corpus":[95],"guide":[97,170],"Rather":[99],"than":[100],"treating":[101],"texts":[102],"as":[103,109,167],"side":[104],"signals,":[105,219],"SAERec":[106],"leverages":[107],"them":[108],"high":[110],"information":[111],"density":[112],"evidence":[113],"construction.":[116],"Specifically,":[117],"first":[119],"extract":[120],"comprehensive":[122],"latent":[130],"large":[133],"language":[134],"(LLMs)":[136],"using":[138],"sparse":[140],"autoencoder":[141],"(SAE)":[142],"disentangle":[144],"interpret":[146],"text":[147],"embeddings,":[148],"which":[149],"isolates":[150],"intent-related":[151],"semantics":[152],"noise.":[155],"Then,":[156],"each":[158],"user,":[159],"retrieve":[161],"relevant":[162],"priors":[168],"It":[172],"contains":[173],"personal":[174,215],"matching":[176],"user's":[178],"current":[179],"interests":[180],"public":[182,217,237],"capturing":[184],"general":[185],"item":[186],"patterns":[187],"shared":[188],"across":[189],"users":[190],"(e.g.,":[191],"price).":[193],"Finally,":[194],"integrate":[196],"retrieved":[197],"into":[199],"modeling,":[201],"multi-branch":[205],"mechanism":[207],"captures":[209],"temporal":[210],"dependencies":[211],"injects":[213],"both":[214],"followed":[220],"adaptive":[223],"fusion":[224],"layer":[225],"construct":[227],"final":[229],"representation":[231],"Extensive":[234],"experiments":[235],"on":[236],"datasets":[238],"demonstrate":[239],"superiority":[241],"SAERec,":[243],"consistently":[244],"outperforming":[245],"state-of-the-art":[246],"baselines":[247],"while":[248],"providing":[249],"human-understandable":[250],"explanations.":[251]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-19T00:00:00"}