{"id":"https://openalex.org/W7131412014","doi":"https://doi.org/10.1109/icdm65498.2025.00042","title":"MREF: Metric-Based Instance Re-Weighting for Rationale Enhancement","display_name":"MREF: Metric-Based Instance Re-Weighting for Rationale Enhancement","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7131412014","doi":"https://doi.org/10.1109/icdm65498.2025.00042"},"language":null,"primary_location":{"id":"doi:10.1109/icdm65498.2025.00042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm65498.2025.00042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining (ICDM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126785963","display_name":"Yibo Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Yibo Huang","raw_affiliation_strings":["School of Computer Science, The University of Auckland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Auckland","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126814747","display_name":"Zixin Kuang","orcid":null},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Zixin Kuang","raw_affiliation_strings":["School of Computer Science, The University of Auckland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Auckland","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126811497","display_name":"Meng-Fen Chiang","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Meng-Fen Chiang","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111961814","display_name":"Wang Chien Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang-Chien Lee","raw_affiliation_strings":["The Pennsylvania State University,Department of Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.6663336,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"347","last_page":"356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.45559999346733093,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.45559999346733093,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.03680000081658363,"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":0.019099999219179153,"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/quality","display_name":"Quality (philosophy)","score":0.6421999931335449},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.631600022315979},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5900999903678894},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5777000188827515},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5388000011444092},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.40119999647140503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6499000191688538},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6421999931335449},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.631600022315979},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5900999903678894},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5777000188827515},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5388000011444092},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4237000048160553},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.40119999647140503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3937000036239624},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3449000120162964},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31529998779296875},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3001999855041504},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.28049999475479126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdm65498.2025.00042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm65498.2025.00042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining (ICDM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2282821441","https://openalex.org/W2949227999","https://openalex.org/W2970379526","https://openalex.org/W3034649382","https://openalex.org/W3034831508","https://openalex.org/W3034917890","https://openalex.org/W3035503910","https://openalex.org/W3099942180","https://openalex.org/W3100727892","https://openalex.org/W3109862485","https://openalex.org/W3175591618","https://openalex.org/W3201085013","https://openalex.org/W3212191244","https://openalex.org/W4205924343","https://openalex.org/W4312344855","https://openalex.org/W4385567059","https://openalex.org/W4385570561","https://openalex.org/W4385571404","https://openalex.org/W4387058885","https://openalex.org/W4389519119","https://openalex.org/W4389520273","https://openalex.org/W4402727891"],"related_works":[],"abstract_inverted_index":{"Good":[0],"rationale":[1,41,52,77,156],"quality":[2,53,157],"from":[3,108],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"is":[8],"essential":[9],"for":[10,39,183],"reliability":[11],"and":[12,30,94,99,122,124,172,191],"interpretability.":[13],"However,":[14],"the":[15,26,102,112,137,164],"rationales":[16,114,141],"produced":[17,113],"by":[18],"existing":[19,181],"LLMs":[20,182],"still":[21],"have":[22],"shortcomings,":[23],"such":[24],"as":[25],"lack":[27],"of":[28,76,132,142],"informativeness":[29],"faithfulness,":[31,118],"which":[32],"affect":[33],"their":[34],"practical":[35],"applications.":[36],"Reproduction":[37],"experiments":[38],"enhancing":[40],"generation":[42],"present":[43],"significant":[44],"challenges":[45],"due":[46],"to":[47,96,110,129,139,169],"several":[48],"factors.":[49],"To":[50],"study":[51],"in":[54],"an":[55,82],"agnostic":[56],"manner,":[57],"we":[58],"develop":[59],"a":[60],"novel":[61],"framework,":[62],"Metric-guided":[63],"Rationale":[64],"Enhancement":[65],"Framework":[66],"(MREF),":[67],"that":[68,149],"re-weighs":[69],"training":[70,133],"instances":[71],"based":[72],"on":[73,86],"multiple":[74],"aspects":[75],"quality.":[78,144],"Specifically,":[79],"MREF":[80,175],"fine-tunes":[81],"LLM":[83,138],"at":[84],"hand":[85],"two":[87],"benchmark":[88],"multiple-choice":[89],"question":[90],"(MCQ)":[91],"datasets,":[92],"ECQA":[93],"MedMCQA,":[95],"generate":[97],"answers":[98],"rationales.":[100],"In":[101],"fine-tuning":[103],"process,":[104],"it":[105],"exploits":[106],"metrics":[107,162],"ROSCOE":[109,161],"evaluate":[111],"across":[115,158],"five":[116],"dimensions:":[117],"informativeness,":[119],"coherence,":[120],"repetition,":[121],"grammar,":[123],"uses":[125],"these":[126],"metric":[127],"scores":[128],"guide":[130],"re-weighting":[131,152],"instances,":[134],"hence":[135],"encouraging":[136],"emphasize":[140],"higher":[143],"Comprehensive":[145],"experimental":[146],"results":[147],"demonstrate":[148],"this":[150],"metric-guided":[151],"strategy":[153],"significantly":[154],"improves":[155],"all":[159],"evaluated":[160],"over":[163],"baselines":[165],"without":[166],"re-weighting,":[167],"leading":[168],"more":[170],"reliable":[171],"understandable":[173],"outputs.":[174],"can":[176],"be":[177,194],"seamlessly":[178],"integrated":[179],"with":[180],"various":[184],"NLP":[185],"tasks":[186],"beyond":[187],"MCQs.":[188],"Our":[189],"code":[190],"datasets":[192],"will":[193],"made":[195],"available":[196],"upon":[197],"acceptance.":[198]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-26T00:00:00"}