{"id":"https://openalex.org/W4401208776","doi":"https://doi.org/10.1162/tacl_a_00681","title":"State of What Art? A Call for Multi-Prompt LLM Evaluation","display_name":"State of What Art? A Call for Multi-Prompt LLM Evaluation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401208776","doi":"https://doi.org/10.1162/tacl_a_00681"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00681","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00681","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00681/2464098/tacl_a_00681.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_00681/2464098/tacl_a_00681.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035602187","display_name":"Moran Mizrahi","orcid":"https://orcid.org/0000-0003-2732-7372"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Moran Mizrahi","raw_affiliation_strings":["School of Computer Science, The Hebrew University of Jerusalem, Israel. moran.mizrahi@mail.huji.ac.il"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, The Hebrew University of Jerusalem, Israel. moran.mizrahi@mail.huji.ac.il","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113315658","display_name":"Guy Kaplan","orcid":null},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Guy Kaplan","raw_affiliation_strings":["School of Computer Science, The Hebrew University of Jerusalem, Israel. guy.kaplan2@mail.huji.ac.il"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, The Hebrew University of Jerusalem, Israel. guy.kaplan2@mail.huji.ac.il","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013154144","display_name":"Dan Malkin","orcid":null},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Dan Malkin","raw_affiliation_strings":["School of Computer Science, The Hebrew University of Jerusalem, Israel. dan.malkinhueb@mail.huji.ac.il"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, The Hebrew University of Jerusalem, Israel. dan.malkinhueb@mail.huji.ac.il","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089112142","display_name":"Rotem Dror","orcid":null},"institutions":[{"id":"https://openalex.org/I91203450","display_name":"University of Haifa","ror":"https://ror.org/02f009v59","country_code":"IL","type":"education","lineage":["https://openalex.org/I91203450"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Rotem Dror","raw_affiliation_strings":["Department of Information Systems, University of Haifa, Israel. rdror@is.haifa.ac.il"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, University of Haifa, Israel. rdror@is.haifa.ac.il","institution_ids":["https://openalex.org/I91203450"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009660759","display_name":"Dafna Shahaf","orcid":"https://orcid.org/0000-0003-3261-0818"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Dafna Shahaf","raw_affiliation_strings":["School of Computer Science, The Hebrew University of Jerusalem, Israel. dshahaf@cs.huji.ac.il"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, The Hebrew University of Jerusalem, Israel. dshahaf@cs.huji.ac.il","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082136238","display_name":"Gabriel Stanovsky","orcid":"https://orcid.org/0000-0002-2420-8979"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Gabriel Stanovsky","raw_affiliation_strings":["School of Computer Science, The Hebrew University of Jerusalem, Israel. gabriel.stanovsky@mail.huji.ac.il"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, The Hebrew University of Jerusalem, Israel. gabriel.stanovsky@mail.huji.ac.il","institution_ids":["https://openalex.org/I197251160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":26.6611,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":{"value":0.99721907,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"12","issue":null,"first_page":"933","last_page":"949"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9965000152587891,"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/T13629","display_name":"Text Readability and Simplification","score":0.9945999979972839,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8427118062973022},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6445732116699219},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.607191264629364},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4432259500026703},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4347781240940094},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35470283031463623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32827576994895935},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08817693591117859},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.08680978417396545}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8427118062973022},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6445732116699219},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.607191264629364},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4432259500026703},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4347781240940094},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35470283031463623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32827576994895935},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08817693591117859},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.08680978417396545},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00681","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00681","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00681/2464098/tacl_a_00681.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:doaj.org/article:175836b0017c4e128aa7c6a99da58716","is_oa":true,"landing_page_url":"https://doaj.org/article/175836b0017c4e128aa7c6a99da58716","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 12 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00681","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00681","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00681/2464098/tacl_a_00681.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":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401208776.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1979354511","https://openalex.org/W2045260557","https://openalex.org/W3196731672","https://openalex.org/W4205991051","https://openalex.org/W4221143046","https://openalex.org/W4224308101","https://openalex.org/W4226040778","https://openalex.org/W4241025692","https://openalex.org/W4281690148","https://openalex.org/W4307079201","https://openalex.org/W4307288829","https://openalex.org/W4311642023","https://openalex.org/W4322718191","https://openalex.org/W4378189609","https://openalex.org/W4378465191","https://openalex.org/W4379958452","https://openalex.org/W4380353763","https://openalex.org/W4385570984","https://openalex.org/W4385571157","https://openalex.org/W4385571633","https://openalex.org/W4385571789","https://openalex.org/W4389519291","https://openalex.org/W4389520255","https://openalex.org/W4389521024","https://openalex.org/W4390041933","https://openalex.org/W4401042935","https://openalex.org/W4402670305","https://openalex.org/W6782879696","https://openalex.org/W6800875267","https://openalex.org/W6802669662","https://openalex.org/W6803084059","https://openalex.org/W6809646742","https://openalex.org/W6810081322","https://openalex.org/W6839193947","https://openalex.org/W6847076894","https://openalex.org/W6847118041","https://openalex.org/W6849590751","https://openalex.org/W6850068309","https://openalex.org/W6850625674","https://openalex.org/W6852874933","https://openalex.org/W6853194257","https://openalex.org/W6853403115","https://openalex.org/W6854112902","https://openalex.org/W6855830118","https://openalex.org/W6857660365","https://openalex.org/W6861209067"],"related_works":["https://openalex.org/W4389443772","https://openalex.org/W2548721895","https://openalex.org/W2373456246","https://openalex.org/W380379685","https://openalex.org/W2013265273","https://openalex.org/W4238809000","https://openalex.org/W2786646446","https://openalex.org/W2312871963","https://openalex.org/W2331739042","https://openalex.org/W4386392971"],"abstract_inverted_index":{"Abstract":[0],"Recent":[1],"advances":[2],"in":[3],"LLMs":[4,46],"have":[5],"led":[6],"to":[7,60],"an":[8],"abundance":[9],"of":[10,28,73,98,114],"evaluation":[11],"benchmarks,":[12],"which":[13],"typically":[14],"rely":[15],"on":[16,76],"a":[17,25,71,92],"single":[18],"instruction":[19,29,57,78],"template":[20],"per":[21],"task.":[22],"We":[23,53,101],"create":[24],"large-scale":[26],"collection":[27],"paraphrases":[30],"and":[31,47,66,95,112],"comprehensively":[32],"analyze":[33],"the":[34,110],"brittleness":[35],"introduced":[36],"by":[37],"single-prompt":[38],"evaluations":[39],"across":[40],"6.5M":[41],"instances,":[42],"involving":[43],"20":[44],"different":[45,56,62,83],"39":[48],"tasks":[49],"from":[50],"3":[51],"benchmarks.":[52],"find":[54],"that":[55,103],"templates":[58],"lead":[59],"very":[61],"performance,":[63],"both":[64],"absolute":[65],"relative.":[67],"Instead,":[68],"we":[69],"propose":[70],"set":[72],"diverse":[74],"metrics":[75,105],"multiple":[77],"paraphrases,":[79],"specifically":[80],"tailored":[81],"for":[82],"use":[84],"cases":[85],"(e.g.,":[86],"LLM":[87,99],"vs.":[88],"downstream":[89],"development),":[90],"ensuring":[91],"more":[93],"reliable":[94],"meaningful":[96],"assessment":[97],"capabilities.":[100],"show":[102],"our":[104],"provide":[106],"new":[107],"insights":[108],"into":[109],"strengths":[111],"limitations":[113],"current":[115],"LLMs.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":20},{"year":2025,"cited_by_count":49},{"year":2024,"cited_by_count":19}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2025-10-10T00:00:00"}
