{"id":"https://openalex.org/W7166821844","doi":"https://doi.org/10.18653/v1/2026.acl-long.2171","title":"Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impact","display_name":"Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impact","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166821844","doi":"https://doi.org/10.18653/v1/2026.acl-long.2171"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.2171","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2171","pdf_url":"https://aclanthology.org/2026.acl-long.2171.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.2171.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139755556","display_name":"Michael Hardy","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Hardy","raw_affiliation_strings":["Stanford University Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139845445","display_name":"Yunsung Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunsung Kim","raw_affiliation_strings":["Stanford University Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86148008,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"46832","last_page":"46876"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10102","display_name":"scientometrics and bibliometrics research","score":0.042399998754262924,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10102","display_name":"scientometrics and bibliometrics research","score":0.042399998754262924,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"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/T14330","display_name":"Library Science and Information Systems","score":0.03180000185966492,"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/T13643","display_name":"Artificial Intelligence in Law","score":0.02630000002682209,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/government","display_name":"Government (linguistics)","score":0.2903999984264374},{"id":"https://openalex.org/keywords/risk-management","display_name":"Risk management","score":0.26159998774528503},{"id":"https://openalex.org/keywords/risk-assessment","display_name":"Risk assessment","score":0.2590000033378601}],"concepts":[{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.4271000027656555},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.32919999957084656},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C32896092","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Risk management","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.25780001282691956},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.25060001015663147},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.2475000023841858},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.24619999527931213},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.24529999494552612}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.2171","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2171","pdf_url":"https://aclanthology.org/2026.acl-long.2171.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2603.00883","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2603.00883","pdf_url":"https://arxiv.org/pdf/2603.00883","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.2171","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2171","pdf_url":"https://aclanthology.org/2026.acl-long.2171.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.47564172744750977,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166821844.pdf","grobid_xml":"https://content.openalex.org/works/W7166821844.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"LLMs":[0,37,75,173],"increasingly":[1],"excel":[2],"on":[3,20,43,57,69],"AI":[4],"benchmarks,":[5,21],"but":[6],"doing":[7],"so":[8],"does":[9],"not":[10],"guarantee":[11],"validity":[12],"for":[13,126,148,158],"downstream":[14,22,80],"tasks.This":[15],"study":[16],"contrasts":[17],"LLM":[18,119],"alignment":[19,161],"tasks,":[23],"and,":[24],"importantly":[25],"the":[26,33,47,90,151],"intended":[27,91],"impact":[28,92],"of":[29,35,46,51,82,93,118,128,150,162,172],"those":[30],"tasks.We":[31,155],"evaluate":[32],"performance":[34],"leading":[36],"(i.e.,":[38],"generative":[39],"pre-trained":[40],"base":[41],"models)":[42],"difficult-to-verify":[44],"tasks":[45,59,164],"teaching":[48,83],"and":[49,85,105,133,165],"learning":[50,95],"schoolchildren.Across":[52],"all":[53,129],"LLMs,":[54,142],"inter-model":[55],"behaviors":[56,68],"disparate":[58],"correlate":[60],"higher":[61],"than":[62],"they":[63],"do":[64],"with":[65,79,89,113],"expert":[66],"human":[67],"target":[70],"tasks.These":[71],"biases":[72],"shared":[73,140],"across":[74,141],"are":[76],"poorly":[77],"aligned":[78,88],"measures":[81],"quality":[84],"often":[86],"negatively":[87],"student":[94],"outcomes.Further,":[96],"we":[97],"find":[98],"multi-model":[99],"ensembles,":[100],"both":[101],"unanimous":[102],"model":[103],"voting":[104],"expert-weighting":[106],"by":[107],"benchmark":[108],"performance,":[109],"further":[110],"exacerbate":[111],"misalignment":[112,131,137,152],"learning.We":[114],"measure":[115],"that":[116,134,144],"selection":[117],"and/or":[120],"prompting":[121],"strategy":[122],"only":[123],"reliably":[124],"accounts":[125,147],"15%":[127],"measured":[130],"error":[132,138],"variation":[135],"in":[136,153,174],"is":[139],"suggesting":[143],"common":[145],"pretraining":[146],"much":[149],"these":[154],"demonstrate":[156],"methods":[157],"robustly":[159],"measuring":[160],"complex":[163],"provide":[166],"unique":[167],"insights":[168],"into":[169],"practical":[170],"applications":[171],"high-noise":[175],"contexts.":[176]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2026-07-02T00:00:00"}