{"id":"https://openalex.org/W4416138656","doi":"https://doi.org/10.1162/tacl.a.735","title":"RELIC: Evaluating Complex Reasoning via the Recognition of Languages In-Context","display_name":"RELIC: Evaluating Complex Reasoning via the Recognition of Languages In-Context","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416138656","doi":"https://doi.org/10.1162/tacl.a.735"},"language":"en","primary_location":{"id":"doi:10.1162/tacl.a.735","doi":"https://doi.org/10.1162/tacl.a.735","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl.a.735","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/TACL.a.735/2612412/tacl.a.735.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,"listed_in":["ccf-b","cwts-core","doaj","dongbi-b","jufo-1","norway-2","poland-20","russia-white-list-1"],"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"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/TACL.a.735/2612412/tacl.a.735.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020894677","display_name":"Jackson Petty","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jackson Petty","raw_affiliation_strings":["Department of Linguistics, New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics, New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045250992","display_name":"Michael Y. Hu","orcid":"https://orcid.org/0000-0002-3718-7169","observed_orcids":["https://orcid.org/0000-0002-3718-7169"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Y. Hu","raw_affiliation_strings":["Center for Data Science, New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Data Science, New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394126","display_name":"Wentao Wang","orcid":"https://orcid.org/0000-0001-9919-7488","observed_orcids":["https://orcid.org/0000-0001-9919-7488"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wentao Wang","raw_affiliation_strings":["Center for Data Science, New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Data Science, New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072633418","display_name":"Shauli Ravfogel","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shauli Ravfogel","raw_affiliation_strings":["Center for Data Science, New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Data Science, New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109946254","display_name":"William Merrill","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Merrill","raw_affiliation_strings":["Center for Data Science, New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Data Science, New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081824828","display_name":"Tal Linzen","orcid":"https://orcid.org/0000-0003-0435-6912","observed_orcids":["https://orcid.org/0000-0003-0435-6912"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tal Linzen","raw_affiliation_strings":["Center for Data Science, New York University","Department of Linguistics, New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Data Science, New York University","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Department of Linguistics, New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5020894677"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01564033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"1410","last_page":"1431"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5278000235557556,"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":0.5278000235557556,"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":0.41359999775886536,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.004999999888241291,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/large-language-models","display_name":"large language models","score":0.8100000023841858},{"id":"https://openalex.org/keywords/complex-reasoning","display_name":"complex reasoning","score":0.7639999985694885},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.6209999918937683},{"id":"https://openalex.org/keywords/reasoning-strategies","display_name":"reasoning strategies","score":0.531000018119812},{"id":"https://openalex.org/keywords/quiet-quitting","display_name":"quiet quitting","score":0.6340000033378601},{"id":"https://openalex.org/keywords/llm-evaluation","display_name":"LLM evaluation","score":0.5529999732971191}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922000288963318},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.723800003528595},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6489999890327454},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5410000085830688},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5078999996185303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4722000062465668},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3806999921798706},{"id":"https://openalex.org/C146072743","wikidata":"https://www.wikidata.org/wiki/Q192161","display_name":"Formal language","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2630999982357025}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1162/tacl.a.735","doi":"https://doi.org/10.1162/tacl.a.735","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl.a.735","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/TACL.a.735/2612412/tacl.a.735.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,"listed_in":["ccf-b","cwts-core","doaj","dongbi-b","jufo-1","norway-2","poland-20","russia-white-list-1"],"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:arXiv.org:2506.05205","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2506.05205","pdf_url":"https://arxiv.org/pdf/2506.05205","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":"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.2506.05205","doi":"https://doi.org/10.48550/arxiv.2506.05205","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.05205","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1162/tacl.a.735","doi":"https://doi.org/10.1162/tacl.a.735","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl.a.735","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/TACL.a.735/2612412/tacl.a.735.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,"listed_in":["ccf-b","cwts-core","doaj","dongbi-b","jufo-1","norway-2","poland-20","russia-white-list-1"],"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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G8645487671","display_name":"CAREER: RI: Structural Linguistic Generalization Through Expert-Designed Tasks","funder_award_id":"2239862","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416138656.pdf","grobid_xml":"https://content.openalex.org/works/W4416138656.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7154632117","https://openalex.org/W7163054852","https://openalex.org/W4417097899","https://openalex.org/W7161231178","https://openalex.org/W6977641929","https://openalex.org/W7214527327","https://openalex.org/W7078209886","https://openalex.org/W4378770449","https://openalex.org/W7213624158","https://openalex.org/W7140120648"],"abstract_inverted_index":{"Abstract":[0],"Large":[1],"language":[2,83],"models":[3,129,176,187],"(LLMs)":[4],"are":[5],"increasingly":[6],"used":[7],"to":[8,34,73,80,95,137,143,184],"solve":[9],"complex":[10,50],"tasks":[11,30],"where":[12],"they":[13,157],"must":[14],"retrieve":[15],"and":[16,40,56,107,110,180],"compose":[17],"many":[18,28],"pieces":[19],"of":[20,63,100,154],"in-context":[21],"information":[22],"in":[23,53,168,172],"long":[24],"reasoning":[25,51,128,155,173],"chains.":[26],"For":[27,186],"real-world":[29],"it":[31],"is":[32],"hard":[33,199],"accurately":[35],"gauge":[36],"how":[37],"model":[38],"performance":[39],"strategy":[41],"change":[42],"as":[43,159,175,195],"task":[44,147,160],"complexity":[45,99,114,161],"grows.":[46],"To":[47],"evaluate":[48],"models\u2019":[49],"capability":[52],"a":[54,66,76,87],"scalable":[55],"verifiable":[57],"way,":[58],"we":[59],"introduce":[60],"RELIC":[61],"(Recognition":[62],"Languages":[64],"In-Context),":[65],"framework":[67],"that":[68,123,165],"evaluates":[69],"an":[70],"LLM\u2019s":[71],"ability":[72],"decide":[74],"whether":[75],"given":[77],"string":[78,108],"belongs":[79],"the":[81,97,101,125,152],"context-free":[82],"(CFL)":[84],"generated":[85],"by":[86,103],"grammar":[88,105],"presented":[89],"in-context.":[90],"CFL":[91],"recognition":[92],"allows":[93],"us":[94],"modulate":[96],"intrinsic":[98],"problem":[102],"varying":[104],"size":[106],"length":[109],"translate":[111],"this":[112,193],"asymptotic":[113],"into":[115],"predictions":[116],"for":[117],"ideal":[118],"LLM":[119],"performance.":[120],"We":[121,163],"find":[122,164],"even":[124,150],"most":[126],"advanced":[127],"perform":[130],"poorly":[131],"on":[132,198],"RELIC,":[133],"not":[134],"only":[135],"failing":[136],"appropriately":[138],"scale":[139],"their":[140],"inference":[141],"compute":[142,169],"keep":[144],"pace":[145],"with":[146],"difficulty,":[148],"but":[149],"reducing":[151],"number":[153],"tokens":[156],"use":[158],"increases.":[162],"these":[166],"decreases":[167],"accompany":[170],"changes":[171],"strategy,":[174],"move":[177],"from":[178],"identifying":[179],"implementing":[181],"algorithmic":[182],"solutions":[183],"guessing.":[185],"whose":[188],"full":[189],"completions":[190],"go":[191],"uninspected,":[192],"manifests":[194],"\u201cquiet":[196],"quitting\u201d":[197],"tasks.":[200],"Code:":[201],"https://jpetty.org/relic":[202]},"counts_by_year":[],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2025-10-10T00:00:00"}