{"id":"https://openalex.org/W7166838852","doi":"https://doi.org/10.18653/v1/2026.acl-long.45","title":"What Makes Good Instruction-Tuning Data? An In-Context Learning Perspective","display_name":"What Makes Good Instruction-Tuning Data? An In-Context Learning Perspective","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166838852","doi":"https://doi.org/10.18653/v1/2026.acl-long.45"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.45","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.45","pdf_url":"https://aclanthology.org/2026.acl-long.45.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 64th Annual Meeting 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/2026.acl-long.45.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013948381","display_name":"Guangzeng Han","orcid":null},"institutions":[{"id":"https://openalex.org/I94658018","display_name":"University of Memphis","ror":"https://ror.org/01cq23130","country_code":"US","type":"education","lineage":["https://openalex.org/I94658018"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guangzeng Han","raw_affiliation_strings":["University of Memphis University of Memphis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Memphis University of Memphis","institution_ids":["https://openalex.org/I94658018"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134843988","display_name":"Xiaolei Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I94658018","display_name":"University of Memphis","ror":"https://ror.org/01cq23130","country_code":"US","type":"education","lineage":["https://openalex.org/I94658018"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaolei Huang","raw_affiliation_strings":["University of Memphis University of Memphis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Memphis University of Memphis","institution_ids":["https://openalex.org/I94658018"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I94658018"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87369468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1013","last_page":"1027"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13405","display_name":"Educational Assessment and Improvement","score":0.15219999849796295,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13405","display_name":"Educational Assessment and Improvement","score":0.15219999849796295,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12884","display_name":"Educational Assessment and Pedagogy","score":0.0348999984562397,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11122","display_name":"Online Learning and Analytics","score":0.03370000049471855,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/perspective","display_name":"Perspective (graphical)","score":0.6712999939918518},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.29679998755455017},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2759000062942505},{"id":"https://openalex.org/keywords/experiential-learning","display_name":"Experiential learning","score":0.26440000534057617}],"concepts":[{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6712999939918518},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.4618000090122223},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3910999894142151},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.3425999879837036},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32600000500679016},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2768999934196472},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2703000009059906},{"id":"https://openalex.org/C37228920","wikidata":"https://www.wikidata.org/wiki/Q1307600","display_name":"Experiential learning","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.45","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.45","pdf_url":"https://aclanthology.org/2026.acl-long.45.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.45","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.45","pdf_url":"https://aclanthology.org/2026.acl-long.45.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6132266521453857,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5912204943","display_name":"Equipment: MRI: Track 2 Acquisition of a HPC Cluster for Fostering Interdisciplinary Collaboration on AI-driven and Data-intensive Research and Education in West Tennessee","funder_award_id":"2318210","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8010155415","display_name":"I-Corps: Translation potential of using artificial intelligence for headache diagnosis","funder_award_id":"2434589","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/W7166838852.pdf","grobid_xml":"https://content.openalex.org/works/W7166838852.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Instruction-tuning":[0],"datasets":[1],"often":[2],"contain":[3],"substantial":[4],"redundancy":[5],"and":[6,64,76],"low-quality":[7],"samples,":[8],"necessitating":[9],"effective":[10,49],"data":[11,17,52,88],"selection":[12,18],"methods.We":[13],"propose":[14],"an":[15,54],"instruction":[16,50,70],"framework":[19],"based":[20],"on":[21],"weighted":[22],"in-context":[23,62,66,99],"influence":[24,67],"(wICI),":[25],"which":[26],"measures":[27],"how":[28,65],"effectively":[29],"each":[30],"candidate":[31],"example":[32],"reduces":[33],"instructionfollowing":[34],"difficulty":[35,59,95],"for":[36],"semantically":[37],"related":[38],"peers.Through":[39],"systematic":[40],"experiments,":[41],"we":[42],"address":[43],"three":[44],"key":[45],"questions:":[46],"what":[47],"constitutes":[48],"tuning":[51,71],"from":[53],"incontext":[55],"perspective,":[56],"whether":[57],"sample":[58,94],"correlates":[60,97],"with":[61,98],"influence,":[63],"translates":[68],"to":[69],"effectiveness.Experiments":[72],"across":[73],"multiple":[74],"models":[75],"benchmarks":[77],"demonstrate":[78],"that":[79,93],"our":[80],"method":[81],"consistently":[82],"outperforms":[83],"existing":[84],"baselines":[85],"under":[86],"constrained":[87],"budgets,":[89],"while":[90],"empirically":[91],"showing":[92],"negatively":[96],"influence.":[100],"1":[101]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}