{"id":"https://openalex.org/W4416034038","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.930","title":"Distilling Many-Shot In-Context Learning into a Cheat Sheet","display_name":"Distilling Many-Shot In-Context Learning into a Cheat Sheet","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034038","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.930"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.930","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.930","pdf_url":"https://aclanthology.org/2025.findings-emnlp.930.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.930.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071438625","display_name":"Ukyo Honda","orcid":"https://orcid.org/0000-0002-4894-9886"},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ukyo Honda","raw_affiliation_strings":["CyberAgent , Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CyberAgent , Tokyo , Japan","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041386745","display_name":"Soichiro Murakami","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Soichiro Murakami","raw_affiliation_strings":["CyberAgent , Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CyberAgent , Tokyo , Japan","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090744564","display_name":"Peinan Zhang","orcid":"https://orcid.org/0009-0007-6541-1029"},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Peinan Zhang","raw_affiliation_strings":["CyberAgent , Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CyberAgent , Tokyo , Japan","institution_ids":["https://openalex.org/I4210089607"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15682222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17158","last_page":"17178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.3041999936103821,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.3041999936103821,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.09149999916553497,"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"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.06800000369548798,"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/set","display_name":"Set (abstract data type)","score":0.32499998807907104},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3140000104904175},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.28529998660087585},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.2793000042438507},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2678000032901764}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5174000263214111},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3440999984741211},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.24899999797344208},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.24310000240802765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.930","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.930","pdf_url":"https://aclanthology.org/2025.findings-emnlp.930.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.930","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.930","pdf_url":"https://aclanthology.org/2025.findings-emnlp.930.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034038.pdf","grobid_xml":"https://content.openalex.org/works/W4416034038.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,95],"large":[3],"language":[4],"models":[5],"(LLMs)":[6],"enable":[7],"effective":[8],"in-context":[9],"learning":[10],"(ICL)":[11],"with":[12,71],"many-shot":[13,39,69],"examples,":[14],"but":[15],"at":[16,52],"the":[17,36,50],"cost":[18],"of":[19],"high":[20],"computational":[21],"demand":[22],"due":[23],"to":[24],"longer":[25],"input":[26],"tokens.To":[27],"address":[28],"this,":[29],"we":[30],"propose":[31],"cheat-sheet":[32,61,86],"ICL,":[33],"which":[34],"distills":[35],"information":[37],"from":[38],"ICL":[40,62,70,78,87],"into":[41],"a":[42,89],"concise":[43],"textual":[44],"summary":[45],"(cheat":[46],"sheet)":[47],"used":[48],"as":[49],"context":[51],"inference":[53],"time.Experiments":[54],"on":[55],"challenging":[56],"reasoning":[57],"tasks":[58],"show":[59],"that":[60,85],"achieves":[63],"comparable":[64],"or":[65],"better":[66],"performance":[67],"than":[68],"far":[72],"fewer":[73],"tokens,":[74],"and":[75],"matches":[76],"retrieval-based":[77],"without":[79],"requiring":[80],"test-time":[81],"retrieval.These":[82],"findings":[83],"demonstrate":[84],"is":[88],"practical":[90],"alternative":[91],"for":[92],"leveraging":[93],"LLMs":[94],"downstream":[96],"tasks.":[97],"1":[98]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}