{"id":"https://openalex.org/W7225174207","doi":"https://doi.org/10.48550/arxiv.2611.02432","title":"Diagnosing Model--Item Interactions in Language Model Benchmarks with LSIRM","display_name":"Diagnosing Model--Item Interactions in Language Model Benchmarks with LSIRM","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225174207","doi":"https://doi.org/10.48550/arxiv.2611.02432"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.02432","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02432","pdf_url":"https://arxiv.org/pdf/2611.02432","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.02432","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160435232","display_name":"Jinwen Luo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luo, Jinwen","raw_affiliation_strings":["University of California , Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160467561","display_name":"Han Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiang, Han","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160552910","display_name":"Ziang Xiao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao, Ziang","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160483007","display_name":"Susu Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Susu","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"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/T10028","display_name":"Topic Modeling","score":0.7738999724388123,"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":0.7738999724388123,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.09030000120401382,"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/T10467","display_name":"Psychometric Methodologies and Testing","score":0.026399999856948853,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/language-model-benchmarking","display_name":"language model benchmarking","score":0.7300000190734863},{"id":"https://openalex.org/keywords/answer-scoring","display_name":"answer scoring","score":0.3799999952316284},{"id":"https://openalex.org/keywords/model-ranking","display_name":"model ranking","score":0.6269999742507935},{"id":"https://openalex.org/keywords/item-properties","display_name":"item properties","score":0.3970000147819519},{"id":"https://openalex.org/keywords/mmlu-pro","display_name":"MMLU-Pro","score":0.6639999747276306},{"id":"https://openalex.org/keywords/gpqa","display_name":"GPQA","score":0.7730000019073486},{"id":"https://openalex.org/keywords/llm-evaluation","display_name":"LLM evaluation","score":0.4830000102519989}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6459000110626221},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5299000144004822},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5218999981880188},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4999000132083893},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.486299991607666},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43619999289512634},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4124000072479248},{"id":"https://openalex.org/C19875794","wikidata":"https://www.wikidata.org/wiki/Q1207340","display_name":"Item response theory","level":3,"score":0.3919999897480011},{"id":"https://openalex.org/C101266164","wikidata":"https://www.wikidata.org/wiki/Q2131821","display_name":"Rasch model","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.31060001254081726},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3059999942779541},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3012000024318695},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.29319998621940613},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C2778883600","wikidata":"https://www.wikidata.org/wiki/Q2390977","display_name":"Language proficiency","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.02432","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02432","pdf_url":"https://arxiv.org/pdf/2611.02432","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2611.02432","doi":"https://doi.org/10.48550/arxiv.2611.02432","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.02432","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2611.02432","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02432","pdf_url":"https://arxiv.org/pdf/2611.02432","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225174207.pdf","grobid_xml":"https://content.openalex.org/works/W7225174207.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415328433","https://openalex.org/W7214754780","https://openalex.org/W7172529290","https://openalex.org/W4392490361","https://openalex.org/W7172149856","https://openalex.org/W7204187820","https://openalex.org/W7164919513","https://openalex.org/W7164047791","https://openalex.org/W7162988157","https://openalex.org/W7206170481"],"abstract_inverted_index":{"Language":[0],"models":[1,54,83],"with":[2,157,176],"similar":[3],"benchmark":[4],"accuracy":[5,233],"can":[6,38],"succeed":[7],"on":[8,55,100,155],"different":[9],"items.":[10,200],"Overall":[11],"scores":[12,208],"do":[13],"not":[14],"show":[15],"where":[16],"their":[17,45,207,210],"performance":[18,81],"differs":[19],"or":[20,112,153],"which":[21,77],"item":[22,34,87,184],"properties":[23,88],"might":[24],"explain":[25],"those":[26],"differences.":[27],"We":[28,50,73,144],"demonstrate":[29],"how":[30,163,236],"the":[31,105,115,139,142,180,202,237],"latent":[32],"space":[33],"response":[35],"model":[36,48,247],"(LSIRM)":[37],"help":[39],"evaluators":[40,227],"investigate":[41],"these":[42,101],"patterns":[43],"and":[44,59,64,71,84,89,93,134,161,234],"consequences":[46],"for":[47],"comparison.":[49],"analyze":[51],"1,348":[52],"language":[53],"5,761":[56,199],"BBH":[57],"items":[58,99,156],"compare":[60],"ways":[61],"of":[62,91,141,190,198,213,239],"presenting":[63],"scoring":[65],"answers":[66,123,160,178,192],"across":[67,82],"BBH,":[68,97],"GPQA,":[69],"MMLU-Pro,":[70],"MuSR.":[72],"examine":[74],"LSIRM":[75],"maps,":[76],"summarize":[78],"differences":[79,182,229],"in":[80,183,215,243],"items,":[85],"alongside":[86],"records":[90],"correct":[92,107,159,177,191],"incorrect":[94],"responses.":[95],"In":[96],"nearby":[98],"maps":[102],"often":[103],"share":[104],"same":[106],"answer,":[108],"such":[109,129],"as":[110,130],"\"Yes\"":[111],"\"No.\"":[113],"Across":[114],"four":[116],"benchmarks,":[117],"this":[118,164],"pattern":[119],"is":[120],"stronger":[121],"when":[122,137],"are":[124],"scored":[125],"using":[126,138],"option":[127],"labels,":[128],"A,":[131],"B,":[132],"C,":[133],"D,":[135],"than":[136],"text":[140],"options.":[143],"then":[145],"estimate":[146],"each":[147],"model's":[148],"tendency":[149,165],"to":[150,167,241],"perform":[151],"better":[152],"worse":[154],"particular":[158],"quantify":[162],"contributes":[166],"its":[168],"score.":[169],"This":[170],"separates":[171],"an":[172],"estimated":[173,203],"contribution":[174,205],"associated":[175],"from":[179,206],"remaining":[181],"performance.":[185],"Two":[186],"models'":[187],"total":[188],"numbers":[189],"differed":[193],"by":[194,231],"only":[195],"14":[196],"out":[197],"Excluding":[201],"answer-category":[204],"moved":[209],"ranks":[211],"hundreds":[212],"places":[214],"opposite":[216],"directions,":[217],"while":[218],"keeping":[219],"all":[220],"other":[221],"estimates":[222],"unchanged.":[223],"The":[224],"approach":[225],"helps":[226],"identify":[228],"hidden":[230],"overall":[232],"understand":[235],"choice":[238],"what":[240],"include":[242],"a":[244],"score":[245],"affects":[246],"rankings.":[248]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-04T00:00:00"}