{"id":"https://openalex.org/W4411630208","doi":"https://doi.org/10.18653/v1/2024.eacl-long.105","title":"Learning to Retrieve In-Context Examples for Large Language Models","display_name":"Learning to Retrieve In-Context Examples for Large Language Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4411630208","doi":"https://doi.org/10.18653/v1/2024.eacl-long.105"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.eacl-long.105","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.105","pdf_url":"https://aclanthology.org/2024.eacl-long.105.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 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.eacl-long.105.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115602506","display_name":"Liang Wang","orcid":"https://orcid.org/0000-0001-5224-8647"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Liang Wang","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102651688","display_name":"Nan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nan Yang","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014662947","display_name":"Furu Wei","orcid":"https://orcid.org/0000-0002-7810-5852"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Furu Wei","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":3.556,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.94675844,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1752","last_page":"1767"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9634000062942505,"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":0.9634000062942505,"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":0.9527999758720398,"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":0.8051969408988953},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6290678977966309},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6200142502784729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5026240348815918},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4941242039203644},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32438021898269653},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.08295753598213196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8051969408988953},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6290678977966309},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6200142502784729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5026240348815918},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4941242039203644},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32438021898269653},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.08295753598213196},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.eacl-long.105","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.105","pdf_url":"https://aclanthology.org/2024.eacl-long.105.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 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.eacl-long.105","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.105","pdf_url":"https://aclanthology.org/2024.eacl-long.105.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 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323029","display_name":"Atomic Energy of Canada Limited","ror":"https://ror.org/019ja9e37"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411630208.pdf","grobid_xml":"https://content.openalex.org/works/W4411630208.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W2349222429","https://openalex.org/W2116230991","https://openalex.org/W3117430770","https://openalex.org/W2046058552","https://openalex.org/W2590751808","https://openalex.org/W1972377868","https://openalex.org/W2132709506","https://openalex.org/W2098730537","https://openalex.org/W2186895195"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"their":[6],"ability":[7,106],"to":[8,13,45,68,79,110],"learn":[9],"in-context,":[10],"allowing":[11],"them":[12],"perform":[14],"various":[15],"tasks":[16,92,112],"based":[17,64,83],"on":[18,31,65,87],"a":[19,42,61,81,88],"few":[20],"input-output":[21],"examples.However,":[22],"the":[23,32,35,70,104,130],"effectiveness":[24],"of":[25,34,72,90,107,136],"in-context":[26,54,99],"learning":[27,100],"is":[28],"heavily":[29],"reliant":[30],"quality":[33,71],"selected":[36],"examples.In":[37],"this":[38],"paper,":[39],"we":[40,102],"propose":[41],"novel":[43],"framework":[44,58,96,109],"iteratively":[46],"train":[47,80],"dense":[48,84],"retrievers":[49],"that":[50,94,118],"can":[51],"identify":[52],"high-quality":[53],"examples":[55,125],"for":[56],"LLMs.Our":[57],"initially":[59],"trains":[60],"reward":[62],"model":[63,120],"LLM":[66],"feedback":[67],"evaluate":[69],"candidate":[73],"examples,":[74],"followed":[75],"by":[76,123],"knowledge":[77],"distillation":[78],"bi-encoder":[82],"retriever.Our":[85],"experiments":[86],"suite":[89],"30":[91],"demonstrate":[93],"our":[95,108,119],"significantly":[97],"enhances":[98],"performance.Furthermore,":[101],"show":[103],"generalization":[105],"unseen":[111],"during":[113],"training.An":[114],"in-depth":[115],"analysis":[116],"reveals":[117],"improves":[121],"performance":[122],"retrieving":[124],"with":[126],"similar":[127],"patterns,":[128],"and":[129,140],"gains":[131],"are":[132,142],"consistent":[133],"across":[134],"LLMs":[135],"varying":[137],"sizes.The":[138],"code":[139],"data":[141],"available":[143],"at":[144]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}