{"id":"https://openalex.org/W4412944787","doi":"https://doi.org/10.18653/v1/2025.acl-long.1135","title":"Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning","display_name":"Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944787","doi":"https://doi.org/10.18653/v1/2025.acl-long.1135"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1135","doi":"https://doi.org/10.18653/v1/2025.acl-long.1135","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1135","pdf_url":"https://aclanthology.org/2025.acl-long.1135.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2025.acl-long.1135.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107930049","display_name":"Shaobo Wang","orcid":"https://orcid.org/0000-0001-8156-7081","observed_orcids":["https://orcid.org/0000-0001-8156-7081"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaobo Wang","raw_affiliation_strings":["EPIC Lab , SJTU","Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPIC Lab , SJTU","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiangqi Jin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangqi Jin","raw_affiliation_strings":["EPIC Lab , SJTU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPIC Lab , SJTU","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451885","display_name":"Ziming Wang","orcid":"https://orcid.org/0000-0002-5457-8882","observed_orcids":["https://orcid.org/0000-0002-5457-8882"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Ziming Wang","raw_affiliation_strings":["EPIC Lab , SJTU","Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPIC Lab , SJTU","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jize Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jize Wang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100319572","display_name":"Jiajun Zhang","orcid":"https://orcid.org/0000-0001-5293-7434","observed_orcids":["https://orcid.org/0000-0001-5293-7434"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Zhang","raw_affiliation_strings":["EPIC Lab , SJTU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPIC Lab , SJTU","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101812386","display_name":"Kaixin Li","orcid":"https://orcid.org/0000-0002-8876-6371","observed_orcids":["https://orcid.org/0000-0002-8876-6371"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kaixin Li","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102635197","display_name":"Zichen Wen","orcid":"https://orcid.org/0009-0002-6157-5898","observed_orcids":["https://orcid.org/0009-0002-6157-5898"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zichen Wen","raw_affiliation_strings":["EPIC Lab , SJTU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPIC Lab , SJTU","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100664779","display_name":"Zhong Li","orcid":"https://orcid.org/0000-0002-3849-3416","observed_orcids":["https://orcid.org/0000-0002-3849-3416","https://orcid.org/0000-0002-7416-1216"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Li","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072088593","display_name":"Conghui He","orcid":"https://orcid.org/0000-0001-8697-695X","observed_orcids":["https://orcid.org/0000-0001-8697-695X","https://orcid.org/0009-0009-3186-6847"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Conghui He","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043651092","display_name":"Xuming Hu","orcid":"https://orcid.org/0000-0001-6075-4224","observed_orcids":["https://orcid.org/0000-0001-6075-4224"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuming Hu","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou )","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100689117","display_name":"Linfeng Zhang","orcid":"https://orcid.org/0000-0002-8470-5846","observed_orcids":["https://orcid.org/0000-0002-8470-5846","https://orcid.org/0000-0002-3341-183X"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linfeng Zhang","raw_affiliation_strings":["EPIC Lab , SJTU","Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPIC Lab , SJTU","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.624,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.97451394,"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":"23287","last_page":"23305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.76419997215271,"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":0.76419997215271,"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":0.19370000064373016,"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":0.012600000016391277,"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/dataset-selection","display_name":"data selection","score":0.7570000290870667},{"id":"https://openalex.org/keywords/llm-fine-tuning","display_name":"LLM fine-tuning","score":0.878000020980835},{"id":"https://openalex.org/keywords/few-shot-prompting","display_name":"few-shot prompting","score":0.9800000190734863},{"id":"https://openalex.org/keywords/computational-cost-reduction","display_name":"computational complexity reduction","score":0.5699999928474426},{"id":"https://openalex.org/keywords/gsm8k","display_name":"GSM8K","score":0.6209999918937683},{"id":"https://openalex.org/keywords/synthetic-dataset","display_name":"synthetic dataset","score":0.4099999964237213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.793671727180481},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6637046933174133},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6378239989280701},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6100651025772095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5143157243728638},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.48249220848083496},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.46722444891929626},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4308130145072937},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07115578651428223},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1135","doi":"https://doi.org/10.18653/v1/2025.acl-long.1135","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1135","pdf_url":"https://aclanthology.org/2025.acl-long.1135.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.12212","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.12212","pdf_url":"https://arxiv.org/pdf/2505.12212","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.12212","doi":"https://doi.org/10.48550/arxiv.2505.12212","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.12212","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:10.18653/v1/2025.acl-long.1135","doi":"https://doi.org/10.18653/v1/2025.acl-long.1135","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1135","pdf_url":"https://aclanthology.org/2025.acl-long.1135.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944787.pdf","grobid_xml":"https://content.openalex.org/works/W4412944787.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W2902287157","https://openalex.org/W3168867926","https://openalex.org/W3198002980","https://openalex.org/W3210904070","https://openalex.org/W4297412003","https://openalex.org/W4307413493","https://openalex.org/W4312107248","https://openalex.org/W4327810158","https://openalex.org/W4385569970","https://openalex.org/W4385572634","https://openalex.org/W4387561528","https://openalex.org/W4391670794","https://openalex.org/W4392019361","https://openalex.org/W4399657778","https://openalex.org/W4401042532","https://openalex.org/W4401042981","https://openalex.org/W4401306886","https://openalex.org/W4401660192","https://openalex.org/W4402667093","https://openalex.org/W4402671223","https://openalex.org/W4402671241","https://openalex.org/W4402671749","https://openalex.org/W4402951277","https://openalex.org/W4403573545","https://openalex.org/W4403573649","https://openalex.org/W4403707319","https://openalex.org/W4403883690","https://openalex.org/W4404782488","https://openalex.org/W4411119917","https://openalex.org/W4412889980","https://openalex.org/W4414281281","https://openalex.org/W4415796759","https://openalex.org/W4415797451","https://openalex.org/W4416034460","https://openalex.org/W4416296080"],"related_works":["https://openalex.org/W4404390762","https://openalex.org/W4403883690","https://openalex.org/W4396718180","https://openalex.org/W4402386675","https://openalex.org/W6979240938","https://openalex.org/W4414981092","https://openalex.org/W4415249938","https://openalex.org/W7169848199","https://openalex.org/W4410298343","https://openalex.org/W4399911507"],"abstract_inverted_index":{"Fine-tuning":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"on":[5,40,51,88,110],"task-specific":[6],"data":[7,31],"is":[8,45,133],"essential":[9],"for":[10,21],"their":[11],"effective":[12],"deployment.As":[13],"dataset":[14,109],"sizes":[15],"grow,":[16],"efficiently":[17],"selecting":[18],"optimal":[19],"subsets":[20],"training":[22],"becomes":[23],"crucial":[24],"to":[25,55,82,105],"balancing":[26],"performance":[27,103],"and":[28,47,91,97,120,128],"computational":[29],"costs.Traditional":[30],"selection":[32],"methods":[33,123],"often":[34],"require":[35],"fine-tuning":[36],"a":[37,125,129],"scoring":[38],"model":[39,81],"the":[41,58,80,106,111,118],"target":[42],"dataset,":[43],"which":[44],"timeconsuming":[46],"resource-intensive,":[48],"or":[49],"rely":[50],"heuristics":[52],"that":[53,74],"fail":[54],"fully":[56],"leverage":[57],"model's":[59],"predictive":[60],"capabilities.To":[61],"address":[62],"these":[63],"challenges,":[64],"we":[65],"propose":[66],"Data":[67,99],"Whisperer,":[68],"an":[69],"efficient,":[70],"training-free,":[71],"attention-based":[72],"method":[73],"leverages":[75],"few-shot":[76],"in-context":[77],"learning":[78],"with":[79,124],"be":[83],"fine-tuned.Comprehensive":[84],"evaluations":[85],"were":[86],"conducted":[87],"both":[89],"raw":[90],"synthetic":[92],"datasets":[93],"across":[94],"diverse":[95],"tasks":[96],"models.Notably,":[98],"Whisperer":[100],"achieves":[101],"superior":[102],"compared":[104],"full":[107],"GSM8K":[108],"Llama-3-8B-Instruct":[112],"model,":[113],"using":[114],"just":[115],"10%":[116],"of":[117],"data,":[119],"outperforms":[121],"existing":[122],"3.1-point":[126],"improvement":[127],"7.4\u00d7":[130],"speedup.The":[131],"code":[132],"available":[134],"at":[135],"https:":[136],"//github.com/gszfwsb/Data-Whisperer.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":8}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-10T00:00:00"}