{"id":"https://openalex.org/W4416034827","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.659","title":"Summarize-Exemplify-Reflect: Data-driven Insight Distillation Empowers LLMs for Few-shot Tabular Classification","display_name":"Summarize-Exemplify-Reflect: Data-driven Insight Distillation Empowers LLMs for Few-shot Tabular Classification","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034827","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.659"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.659","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.659","pdf_url":"https://aclanthology.org/2025.findings-emnlp.659.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.659.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yifei Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifei Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045031866","display_name":"Jingmei Li","orcid":"https://orcid.org/0009-0009-5596-1953"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiatong Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457938","display_name":"Weijia Zhang","orcid":"https://orcid.org/0000-0001-8103-5325"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weijia Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063466614","display_name":"Mohammad Aliannejadi","orcid":"https://orcid.org/0000-0002-9447-4172"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammad Aliannejadi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055639036","display_name":"Evangelos Kanoulas","orcid":"https://orcid.org/0000-0002-8312-0694"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Evangelos Kanoulas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103128873","display_name":"Renjun Hu","orcid":"https://orcid.org/0000-0002-1094-6890"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Renjun Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.22131415,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12324","last_page":"12348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.23180000483989716,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.23180000483989716,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.09510000050067902,"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/T10028","display_name":"Topic Modeling","score":0.07840000092983246,"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/reflection","display_name":"Reflection (computer programming)","score":0.5738000273704529},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.44850000739097595},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.32580000162124634},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2793999910354614}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6607999801635742},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.5738000273704529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47609999775886536},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.45570001006126404},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.44850000739097595},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36340001225471497},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.33180001378059387},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3061000108718872},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25130000710487366},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.659","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.659","pdf_url":"https://aclanthology.org/2025.findings-emnlp.659.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"},{"id":"pmh:doi:10.3929/ethz-c-000795378","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/795378","pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.659","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.659","pdf_url":"https://aclanthology.org/2025.findings-emnlp.659.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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034827.pdf","grobid_xml":"https://content.openalex.org/works/W4416034827.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"studies":[1,112],"show":[2],"the":[3,19,92,115],"promise":[4],"of":[5,56,95],"large":[6],"language":[7],"models":[8],"(LLMs)":[9],"for":[10],"few-shot":[11],"tabular":[12,38,97],"classification":[13,39],"but":[14],"highlight":[15],"challenges":[16],"due":[17],"to":[18,33,83],"variability":[20],"in":[21,125],"structured":[22],"data.To":[23],"address":[24],"this,":[25],"we":[26,46],"propose":[27],"distilling":[28],"data":[29,76,128],"into":[30],"actionable":[31],"insights":[32,80],"enable":[34,81],"robust":[35],"and":[36,59,67,75,89,119,129],"effective":[37],"by":[40,54],"LLMs.Inspired":[41],"from":[42],"human":[43],"learning":[44],"processes,":[45],"introduce":[47],"InsightTab,":[48],"an":[49],"insight":[50,68],"distillation":[51,117],"framework":[52],"guided":[53],"principles":[55],"divide-and-conquer,":[57],"easy-first,":[58],"reflective":[60],"learning.It":[61],"integrates":[62],"rule":[63],"summarization,":[64],"strategic":[65],"exemplification,":[66],"reflection":[69],"through":[70],"deep":[71],"collaboration":[72],"between":[73],"LLMs":[74,82],"modeling":[77],"techniques.The":[78],"obtained":[79],"better":[84],"align":[85],"their":[86],"general":[87],"knowledge":[88],"capabilities":[90],"with":[91],"particular":[93],"requirements":[94],"specific":[96],"tasks.We":[98],"extensively":[99],"evaluate":[100],"InsightTab":[101],"on":[102],"nine":[103],"datasets.The":[104],"results":[105],"demonstrate":[106],"consistent":[107],"improvement":[108],"over":[109],"state-of-the-art":[110],"methods.Ablation":[111],"further":[113],"validate":[114],"principleguided":[116],"process,":[118],"in-depth":[120],"analyses":[121],"emphasize":[122],"InsightTab's":[123],"effectiveness":[124],"leveraging":[126],"labeled":[127],"managing":[130],"biases.":[131]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-11-08T00:00:00"}