{"id":"https://openalex.org/W4417453595","doi":"https://doi.org/10.48550/arxiv.2512.13077","title":"LikeBench: Evaluating Subjective Likability in LLMs for Personalization","display_name":"LikeBench: Evaluating Subjective Likability in LLMs for Personalization","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W4417453595","doi":"https://doi.org/10.48550/arxiv.2512.13077"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2512.13077","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.13077","pdf_url":"https://arxiv.org/pdf/2512.13077","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.13077","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120842104","display_name":"Md Awsafur Rahman","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Rahman, Md Awsafur","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120842105","display_name":"Adam Gabrys","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gabrys, Adam","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Kang, Doug","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Doug","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112385962","display_name":"J. Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Jingjing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Tan, Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Tian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5120842106","display_name":"Ashwin Chandramouli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chandramouli, Ashwin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5120842104"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T14074","display_name":"Persona Design and Applications","score":0.9308000206947327,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T14074","display_name":"Persona Design and Applications","score":0.9308000206947327,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T12607","display_name":"Personal Information Management and User Behavior","score":0.00860000029206276,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.006200000178068876,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.7335000038146973},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6304000020027161},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5030999779701233},{"id":"https://openalex.org/keywords/trait","display_name":"Trait","score":0.4966999888420105},{"id":"https://openalex.org/keywords/formality","display_name":"Formality","score":0.45410001277923584},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4336000084877014},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41780000925064087},{"id":"https://openalex.org/keywords/persona","display_name":"Persona","score":0.3952000141143799}],"concepts":[{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.7335000038146973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6934000253677368},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6304000020027161},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5030999779701233},{"id":"https://openalex.org/C106934330","wikidata":"https://www.wikidata.org/wiki/Q1971873","display_name":"Trait","level":2,"score":0.4966999888420105},{"id":"https://openalex.org/C2777159308","wikidata":"https://www.wikidata.org/wiki/Q1757948","display_name":"Formality","level":2,"score":0.45410001277923584},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4336000084877014},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41780000925064087},{"id":"https://openalex.org/C313442","wikidata":"https://www.wikidata.org/wiki/Q778556","display_name":"Persona","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3849000036716461},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.3424000144004822},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3379000127315521},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C67712803","wikidata":"https://www.wikidata.org/wiki/Q7901853","display_name":"User modeling","level":3,"score":0.33180001378059387},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32249999046325684},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3149999976158142},{"id":"https://openalex.org/C108170787","wikidata":"https://www.wikidata.org/wiki/Q3951828","display_name":"Agency (philosophy)","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C27286358","wikidata":"https://www.wikidata.org/wiki/Q6031027","display_name":"Information cascade","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2678999900817871},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C131158328","wikidata":"https://www.wikidata.org/wiki/Q1307337","display_name":"Social influence","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C2779136372","wikidata":"https://www.wikidata.org/wiki/Q10283002","display_name":"Information flow","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2512.13077","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.13077","pdf_url":"https://arxiv.org/pdf/2512.13077","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.13077","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.13077","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.13077","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.13077","pdf_url":"https://arxiv.org/pdf/2512.13077","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417453595.pdf","grobid_xml":"https://content.openalex.org/works/W4417453595.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"A":[0],"personalized":[1],"LLM":[2,22,85],"should":[3],"remember":[4],"user":[5,19,33,56,109,192],"facts,":[6],"apply":[7],"them":[8],"correctly,":[9],"and":[10,35,53,110,128,175,195],"adapt":[11,87,125,258],"over":[12,88],"time":[13,89],"to":[14,55,90,94,124,126,155,181],"provide":[15,95],"responses":[16],"that":[17,45,75,220],"the":[18,101,115,119,141,146,153,190,206],"prefers.":[20],"Existing":[21],"personalization":[23],"benchmarks":[24],"are":[25,133,152],"largely":[26],"centered":[27],"on":[28,242],"two":[29],"axes:":[30],"accurately":[31,36],"recalling":[32],"information":[34,39],"applying":[37],"remembered":[38],"in":[40,104,214,260,268],"downstream":[41],"tasks.":[42],"We":[43],"argue":[44],"a":[46,70,91,107,184],"third":[47],"axis,":[48],"likability,":[49],"is":[50],"both":[51],"subjective":[52],"central":[54],"experience,":[57],"yet":[58],"under-measured":[59],"by":[60,81,140,240],"current":[61],"benchmarks.":[62],"To":[63,145,188],"measure":[64],"likability":[65,77,136,157,243],"holistically,":[66],"we":[67,151],"introduce":[68],"LikeBench,":[69,100],"multi-session,":[71],"dynamic":[72],"evaluation":[73],"framework":[74],"measures":[76],"across":[78,137],"multiple":[79,159],"dimensions":[80,139],"how":[82],"much":[83],"an":[84],"can":[86],"user's":[92],"preferences":[93,112],"more":[96,193],"likable":[97],"responses.":[98],"In":[99],"LLMs":[102],"engage":[103],"conversation":[105,170],"with":[106,231],"simulated":[108,143,191],"learn":[111],"only":[113,265],"from":[114],"ongoing":[116],"dialogue.":[117],"As":[118],"interaction":[120],"unfolds,":[121],"models":[122,255],"try":[123],"responses,":[127],"after":[129],"each":[130],"turn,":[131],"they":[132],"evaluated":[134],"for":[135],"seven":[138],"same":[142],"user.":[144],"best":[147],"of":[148],"our":[149],"knowledge,":[150],"first":[154],"decompose":[156],"into":[158],"diagnostic":[160],"metrics:":[161],"emotional":[162],"adaptation,":[163,167],"formality":[164],"matching,":[165],"knowledge":[166],"reference":[168],"understanding,":[169],"length":[171],"fit,":[172,174],"humor":[173],"callback,":[176],"which":[177],"makes":[178],"it":[179],"easier":[180],"pinpoint":[182],"where":[183],"model":[185],"falls":[186],"short.":[187],"make":[189],"realistic":[194],"discriminative,":[196],"LikeBench":[197],"uses":[198],"fine-grained,":[199],"psychologically":[200],"grounded":[201],"descriptive":[202],"personas":[203,212],"rather":[204],"than":[205],"coarse":[207],"high/low":[208],"trait":[209],"rating":[210],"based":[211],"used":[213],"prior":[215],"work.":[216],"Our":[217],"benchmark":[218],"shows":[219],"strong":[221],"memory":[222,233,248],"performance":[223],"does":[224],"not":[225],"guarantee":[226],"high":[227],"likability:":[228],"DeepSeek":[229],"R1,":[230],"lower":[232],"accuracy":[234,249],"(86%,":[235],"17":[236],"facts/profile),":[237],"outperformed":[238],"Qwen3":[239],"28%":[241],"score":[244],"despite":[245],"Qwen3's":[246],"higher":[247],"(93%,":[250],"43":[251],"facts/profile).":[252],"Even":[253],"SOTA":[254],"like":[256],"GPT-5":[257],"well":[259],"short":[261],"exchanges":[262],"but":[263],"show":[264],"limited":[266],"robustness":[267],"longer,":[269],"noisier":[270],"interactions.":[271]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-12-17T00:00:00"}