{"id":"https://openalex.org/W4404132421","doi":"https://doi.org/10.1162/tacl_a_00710","title":"Beyond Prompt Brittleness: Evaluating the Reliability and Consistency of Political Worldviews in LLMs","display_name":"Beyond Prompt Brittleness: Evaluating the Reliability and Consistency of Political Worldviews in LLMs","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404132421","doi":"https://doi.org/10.1162/tacl_a_00710"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00710","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00710","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00710/2478626/tacl_a_00710.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00710/2478626/tacl_a_00710.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057586513","display_name":"Tanise Ceron","orcid":"https://orcid.org/0009-0002-4845-2789"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tanise Ceron","raw_affiliation_strings":["Institute for Natural Language Processing, University of Stuttgart, Germany. tanise.ceron@ims.uni-stuttgart.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing, University of Stuttgart, Germany. tanise.ceron@ims.uni-stuttgart.de","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094028017","display_name":"Neele Falk","orcid":null},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Neele Falk","raw_affiliation_strings":["Institute for Natural Language Processing, University of Stuttgart, Germany. neele.falk@ims.uni-stuttgart.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing, University of Stuttgart, Germany. neele.falk@ims.uni-stuttgart.de","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094028018","display_name":"Ana Bari\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I181343428","display_name":"University of Zagreb","ror":"https://ror.org/00mv6sv71","country_code":"HR","type":"education","lineage":["https://openalex.org/I181343428"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"Ana Bari\u0107","raw_affiliation_strings":["Faculty of Electrical Engineering and Computing, University of Zagreb, Croatia. ana.baric@fer.hr"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Computing, University of Zagreb, Croatia. ana.baric@fer.hr","institution_ids":["https://openalex.org/I181343428"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042580443","display_name":"Dmitry Nikolaev","orcid":"https://orcid.org/0000-0002-3034-9794"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dmitry Nikolaev","raw_affiliation_strings":["Department of Linguistics and English Language, University of Manchester, UK. dmitry.nikolaev@manchester.ac.uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics and English Language, University of Manchester, UK. dmitry.nikolaev@manchester.ac.uk","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003870894","display_name":"Sebastian Pad\u00f3","orcid":"https://orcid.org/0000-0002-7529-6825"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Pad\u00f3","raw_affiliation_strings":["Institute for Natural Language Processing, University of Stuttgart, Germany. pado@ims.uni-stuttgart.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing, University of Stuttgart, Germany. pado@ims.uni-stuttgart.de","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":43.8362,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.99831586,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"12","issue":null,"first_page":"1378","last_page":"1400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12755","display_name":"Legal Education and Practice Innovations","score":0.972100019454956,"subfield":{"id":"https://openalex.org/subfields/3308","display_name":"Law"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12755","display_name":"Legal Education and Practice Innovations","score":0.972100019454956,"subfield":{"id":"https://openalex.org/subfields/3308","display_name":"Law"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12225","display_name":"Political Influence and Corporate Strategies","score":0.9448000192642212,"subfield":{"id":"https://openalex.org/subfields/1408","display_name":"Strategy and Management"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12185","display_name":"Regulation and Compliance Studies","score":0.9424999952316284,"subfield":{"id":"https://openalex.org/subfields/1408","display_name":"Strategy and Management"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.7604491710662842},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.7358854413032532},{"id":"https://openalex.org/keywords/politics","display_name":"Politics","score":0.6360524892807007},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.500910758972168},{"id":"https://openalex.org/keywords/brittleness","display_name":"Brittleness","score":0.48395588994026184},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.3885580003261566},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.3421659469604492},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.28014612197875977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14365142583847046},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13624513149261475},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.12189733982086182},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.09573200345039368},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07358190417289734},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.07036483287811279}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7604491710662842},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.7358854413032532},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.6360524892807007},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.500910758972168},{"id":"https://openalex.org/C136478896","wikidata":"https://www.wikidata.org/wiki/Q898288","display_name":"Brittleness","level":2,"score":0.48395588994026184},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.3885580003261566},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3421659469604492},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.28014612197875977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14365142583847046},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13624513149261475},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.12189733982086182},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.09573200345039368},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07358190417289734},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.07036483287811279},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00710","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00710","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00710/2478626/tacl_a_00710.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire/599942eb-5c1b-4cc1-8b10-3a6ee844d289","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/599942eb-5c1b-4cc1-8b10-3a6ee844d289","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ceron, T, Falk, N, Baric, A, Nikolaev, D & Pad\u00f3, S 2024, 'Beyond prompt brittleness : Evaluating the reliability and consistency of political worldviews in LLMs', Transactions of the Association for Computational Linguistics, vol. 12, pp. 1378\u20131400. https://doi.org/10.1162/tacl_a_00710","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00710","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00710","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00710/2478626/tacl_a_00710.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.8199999928474426,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G4486883562","display_name":"MARDY: Modellierung von Argumentationsdynamik im politischen Diskurs (Phase 2)","funder_award_id":"375875969","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404132421.pdf","grobid_xml":"https://content.openalex.org/works/W4404132421.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W1488623428","https://openalex.org/W1493610364","https://openalex.org/W1583837637","https://openalex.org/W1973767321","https://openalex.org/W1998151601","https://openalex.org/W2009659525","https://openalex.org/W2020402250","https://openalex.org/W2074589553","https://openalex.org/W2096940599","https://openalex.org/W2326917780","https://openalex.org/W2332251037","https://openalex.org/W2737923628","https://openalex.org/W3004975108","https://openalex.org/W3037831233","https://openalex.org/W3118781290","https://openalex.org/W3130377749","https://openalex.org/W3133702157","https://openalex.org/W3181414820","https://openalex.org/W3196248941","https://openalex.org/W3198599617","https://openalex.org/W3213104004","https://openalex.org/W3213556453","https://openalex.org/W4212774754","https://openalex.org/W4237556661","https://openalex.org/W4283511031","https://openalex.org/W4287891033","https://openalex.org/W4292372243","https://openalex.org/W4298050500","https://openalex.org/W4307079201","https://openalex.org/W4313559133","https://openalex.org/W4380715567","https://openalex.org/W4382619745","https://openalex.org/W4384918448","https://openalex.org/W4385564993","https://openalex.org/W4385567149","https://openalex.org/W4385570054","https://openalex.org/W4385852384","https://openalex.org/W4386302153","https://openalex.org/W4386566829","https://openalex.org/W4387821331","https://openalex.org/W4388323869","https://openalex.org/W4389524209","https://openalex.org/W4389524362","https://openalex.org/W4391090624","https://openalex.org/W4392260510","https://openalex.org/W4392402185","https://openalex.org/W4400074783","https://openalex.org/W4401042395","https://openalex.org/W4401208776","https://openalex.org/W4402227480","https://openalex.org/W4402683988","https://openalex.org/W6761551260","https://openalex.org/W6788175385","https://openalex.org/W6791446462","https://openalex.org/W6847076894","https://openalex.org/W6851152545","https://openalex.org/W6853514062","https://openalex.org/W6853620503","https://openalex.org/W6854004153","https://openalex.org/W6854866820","https://openalex.org/W6856121608","https://openalex.org/W6858023062","https://openalex.org/W6858224874"],"related_works":["https://openalex.org/W2033512842","https://openalex.org/W4233600955","https://openalex.org/W4322734194","https://openalex.org/W3116237489","https://openalex.org/W2913665393","https://openalex.org/W2369695847","https://openalex.org/W3005535424","https://openalex.org/W2994319598","https://openalex.org/W2047067935","https://openalex.org/W1607054433"],"abstract_inverted_index":{"Abstract":[0],"Due":[1],"to":[2,13,58,115],"the":[3,63,80,167],"widespread":[4],"use":[5],"of":[6,76,84,94,169],"large":[7],"language":[8],"models":[9,128],"(LLMs),":[10],"we":[11],"need":[12],"understand":[14],"whether":[15,52,62],"they":[16],"embed":[17],"a":[18,74,92,143],"specific":[19],"\u201cworldview\u201d":[20],"and":[21,61,69,82,102,118,153,160,172],"what":[22],"these":[23,53],"views":[24],"reflect.":[25],"Recent":[26],"studies":[27],"report":[28],"that,":[29],"prompted":[30],"with":[31,124,133,162],"political":[32,70,88],"questionnaires,":[33],"LLMs":[34,109],"show":[35,129,142],"left-liberal":[36],"leanings":[37,54],"(Feng":[38],"et":[39,43],"al.,":[40,44],"2023;":[41],"Motoki":[42],"2024).":[45],"However,":[46],"it":[47],"is":[48,65],"as":[49],"yet":[50],"unclear":[51],"are":[55],"reliable":[56],"(robust":[57],"prompt":[59],"variations)":[60],"leaning":[64],"consistent":[66,164],"across":[67],"policies":[68],"leaning.":[71],"We":[72,107],"propose":[73],"series":[75],"tests":[77],"which":[78],"assess":[79],"reliability":[81,122],"consistency":[83],"LLMs\u2019":[85],"stances":[86],"on":[87,91],"statements":[89],"based":[90],"dataset":[93],"voting-advice":[95],"questionnaires":[96],"collected":[97],"from":[98,113],"seven":[99],"EU":[100],"countries":[101],"annotated":[103],"for":[104],"policy":[105,139,171],"issues.":[106],"study":[108],"ranging":[110],"in":[111,166],"size":[112],"7B":[114],"70B":[116],"parameters":[117],"find":[119],"that":[120],"their":[121],"increases":[123],"parameter":[125],"count.":[126],"Larger":[127],"overall":[130],"stronger":[131],"alignment":[132],"left-leaning":[134],"parties":[135],"but":[136,156],"differ":[137],"among":[138],"programs:":[140],"They":[141],"(left-wing)":[144],"positive":[145],"stance":[146],"towards":[147],"environment":[148],"protection,":[149],"social":[150],"welfare":[151],"state,":[152],"liberal":[154],"society":[155],"also":[157],"(right-wing)":[158],"law":[159],"order,":[161],"no":[163],"preferences":[165],"areas":[168],"foreign":[170],"migration.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}
