{"id":"https://openalex.org/W7208733282","doi":"https://doi.org/10.18653/2026.emnlp-main.1722","title":"LLMs Learn Better In-Context from Rules than from Examples","display_name":"LLMs Learn Better In-Context from Rules than from Examples","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7208733282","doi":"https://doi.org/10.18653/2026.emnlp-main.1722"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.1722","doi":"https://doi.org/10.18653/2026.emnlp-main.1722","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1722","pdf_url":"https://aclanthology.org/2026.emnlp-main.1722.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-main.1722.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5150041923","display_name":"Xiang Fu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Fu","raw_affiliation_strings":["Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149982124","display_name":"Seungmin Cho","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seungmin Cho","raw_affiliation_strings":["Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001230649","display_name":"Yukyung Lee","orcid":"https://orcid.org/0000-0002-7835-6336","observed_orcids":["https://orcid.org/0000-0002-7835-6336"]},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yukyung Lee","raw_affiliation_strings":["Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5150030318","display_name":"Najoung Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najoung Kim","raw_affiliation_strings":["Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I111088046"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.70637494,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"39279","last_page":"39313"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5199999809265137,"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":0.5199999809265137,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.39649999141693115,"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":0.05169999971985817,"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/in-context-learning","display_name":"in-context learning","score":0.9679999947547913},{"id":"https://openalex.org/keywords/rule-based-learning","display_name":"rule-based learning","score":0.7979999780654907},{"id":"https://openalex.org/keywords/learning-from-examples","display_name":"learning from examples","score":0.9649999737739563},{"id":"https://openalex.org/keywords/few-shot-prompting","display_name":"few-shot prompting","score":0.9010000228881836},{"id":"https://openalex.org/keywords/instruction-following","display_name":"instruction following","score":0.9409999847412109},{"id":"https://openalex.org/keywords/instruction-tuning","display_name":"instruction tuning","score":0.8740000128746033},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8799999952316284},{"id":"https://openalex.org/keywords/algebraic-thinking","display_name":"algebraic thinking","score":0.6949999928474426},{"id":"https://openalex.org/keywords/parametric-knowledge","display_name":"parametric knowledge","score":0.8539999723434448},{"id":"https://openalex.org/keywords/learning-effectiveness","display_name":"learning effectiveness","score":0.3179999887943268}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7008000016212463},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6348000168800354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5526999831199646},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4625999927520752},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45080000162124634},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.44339999556541443},{"id":"https://openalex.org/C32254414","wikidata":"https://www.wikidata.org/wiki/Q4724364","display_name":"Algorithmic learning theory","level":3,"score":0.4163999855518341},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.3409000039100647},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C79416737","wikidata":"https://www.wikidata.org/wiki/Q2305519","display_name":"Social learning","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28369998931884766},{"id":"https://openalex.org/C12298181","wikidata":"https://www.wikidata.org/wiki/Q7246814","display_name":"Proactive learning","level":5,"score":0.2782999873161316},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C48164120","wikidata":"https://www.wikidata.org/wiki/Q4491893","display_name":"Concept learning","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.emnlp-main.1722","doi":"https://doi.org/10.18653/2026.emnlp-main.1722","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1722","pdf_url":"https://aclanthology.org/2026.emnlp-main.1722.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2609.03213","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.03213","pdf_url":"https://arxiv.org/pdf/2609.03213","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.03213","doi":"https://doi.org/10.48550/arxiv.2609.03213","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.03213","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":"doi:10.18653/2026.emnlp-main.1722","doi":"https://doi.org/10.18653/2026.emnlp-main.1722","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1722","pdf_url":"https://aclanthology.org/2026.emnlp-main.1722.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7208733282.pdf","grobid_xml":"https://content.openalex.org/works/W7208733282.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4226024653","https://openalex.org/W4394781845","https://openalex.org/W4388748170","https://openalex.org/W4399453612","https://openalex.org/W4403587666","https://openalex.org/W4411630208","https://openalex.org/W4385571505","https://openalex.org/W4385569978","https://openalex.org/W4388717938","https://openalex.org/W4416384601"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,87],"(LLMs)":[3],"exhibit":[4],"incontext":[5],"learning":[6,22,32,41,50,65,83,127,131,141],"capabilities,":[7],"where":[8],"they":[9],"can":[10],"learn":[11,89],"new":[12],"tasks":[13,51],"from":[14,33,42,92,95],"prompt":[15],"contexts":[16],"without":[17],"weight":[18],"updates.We":[19],"compare":[20,61],"the":[21,70,82,109,123,155,165,175],"efficacies":[23],"of":[24,28,35,44,64,103,111,125,139,158],"two":[25,62],"prominent":[26],"modes":[27,63],"in-context":[29],"learning:":[30],"(1)":[31],"descriptions":[34],"rules":[36,93,104,146,159],"(instruction":[37],"following);":[38],"and":[39,77,98,118,145,170,172],"(2)":[40],"examples":[43,96,100,112,161],"input-output":[45],"demonstrations":[46],"(fewshot":[47],"prompting).Through":[48],"five":[49],"that":[52,80,86],"cover":[53],"diverse":[54],"domains":[55],"(games,":[56],"arithmetic,":[57],"linguistic":[58],"inferences),":[59],"we":[60,134],"(rules":[66],"vs.":[67],"examples)":[68],"specifying":[69],"same":[71],"underlying":[72],"task.We":[73],"furthermore":[74],"explore":[75],"model":[76],"task":[78,153,166,176],"properties":[79],"modulate":[81],"efficacies.We":[84],"find":[85,135],"generally":[88],"more":[90],"reliably":[91],"than":[94],"alone,":[97],"additional":[99],"on":[101],"top":[102],"or":[105],"simply":[106],"scaling":[107],"up":[108],"number":[110],"do":[113],"not":[114],"lead":[115,148],"to":[116,149],"consistent":[117],"significant":[119],"gains.Instruction":[120],"tuning":[121],"amplifies":[122],"benefit":[124],"rule-based":[126],"while":[128],"keeping":[129],"examplebased":[130],"capacities":[132],"intact.Surprisingly,":[133],"no":[136],"privileged":[137],"effect":[138],"example-based":[140],"in":[142,151],"base":[143],"models,":[144],"still":[147],"gains":[150],"algebraic":[152,168],"domains.Overall,":[154],"comparative":[156],"efficacy":[157],"over":[160],"is":[162],"larger":[163],"when":[164,174],"recruits":[167,181],"abstractions":[169],"computations,":[171],"smaller":[173],"requires":[177],"distributional":[178],"sensitivity":[179],"and/or":[180],"parametric":[182],"knowledge.":[183],"datasets/tin-lab/rules_vs_examples":[184],"tinlaboratory/rules-vs-examples":[185]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-09-05T00:00:00"}