{"id":"https://openalex.org/W4400104762","doi":"https://doi.org/10.48550/arxiv.2406.18297","title":"FactFinders at CheckThat! 2024: Refining Check-worthy Statement Detection with LLMs through Data Pruning","display_name":"FactFinders at CheckThat! 2024: Refining Check-worthy Statement Detection with LLMs through Data Pruning","publication_year":2024,"publication_date":"2024-06-26","ids":{"openalex":"https://openalex.org/W4400104762","doi":"https://doi.org/10.48550/arxiv.2406.18297"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.18297","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.18297","pdf_url":"https://arxiv.org/pdf/2406.18297","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.18297","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104337969","display_name":"Yufeng Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Li, Yufeng","raw_affiliation_strings":["School of Electronic Engineering and Computer Science , Queen Mary University of London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science , Queen Mary University of London","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065922952","display_name":"Rrubaa Panchendrarajan","orcid":"https://orcid.org/0000-0002-1403-2236","observed_orcids":["https://orcid.org/0000-0002-1403-2236"]},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Panchendrarajan, Rrubaa","raw_affiliation_strings":["School of Electronic Engineering and Computer Science , Queen Mary University of London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science , Queen Mary University of London","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071220716","display_name":"Arkaitz Zubiaga","orcid":"https://orcid.org/0000-0003-4583-3623","observed_orcids":["https://orcid.org/0000-0003-4583-3623"]},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zubiaga, Arkaitz","raw_affiliation_strings":["School of Electronic Engineering and Computer Science , Queen Mary University of London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science , Queen Mary University of London","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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/T10028","display_name":"Topic Modeling","score":0.002099999925121665,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":9.999999747378752e-05,"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/fact-checking","display_name":"fact-checking","score":0.9259999990463257},{"id":"https://openalex.org/keywords/data-pruning","display_name":"data pruning","score":0.6539999842643738},{"id":"https://openalex.org/keywords/training-data-quality","display_name":"training data quality","score":0.8259999752044678},{"id":"https://openalex.org/keywords/open-source-large-language-models","display_name":"open-source large language models","score":0.9150000214576721},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.7929999828338623},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.8700000047683716}],"concepts":[{"id":"https://openalex.org/C60044698","wikidata":"https://www.wikidata.org/wiki/Q1283324","display_name":"Refining (metallurgy)","level":2,"score":0.7778996229171753},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7209327220916748},{"id":"https://openalex.org/C2777026412","wikidata":"https://www.wikidata.org/wiki/Q2684591","display_name":"Statement (logic)","level":2,"score":0.6158044338226318},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4560104012489319},{"id":"https://openalex.org/C144027150","wikidata":"https://www.wikidata.org/wiki/Q48803","display_name":"Horticulture","level":1,"score":0.13822564482688904},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.11798766255378723},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1115555465221405},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.09415796399116516},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.09405204653739929},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.18297","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.18297","pdf_url":"https://arxiv.org/pdf/2406.18297","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.18297","doi":"https://doi.org/10.48550/arxiv.2406.18297","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.18297","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":"pmh:oai:arXiv.org:2406.18297","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.18297","pdf_url":"https://arxiv.org/pdf/2406.18297","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6046217463","display_name":null,"funder_award_id":"101073351","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320338337","display_name":"H2020 Marie Sk\u0142odowska-Curie Actions","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400104762.pdf","grobid_xml":"https://content.openalex.org/works/W4400104762.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7200117222","https://openalex.org/W7140126496","https://openalex.org/W4401042272","https://openalex.org/W7106782512","https://openalex.org/W3034085606","https://openalex.org/W4396822170","https://openalex.org/W7082047776","https://openalex.org/W4416073435","https://openalex.org/W4404781625","https://openalex.org/W6910635751"],"abstract_inverted_index":{"The":[0,135],"rapid":[1],"dissemination":[2],"of":[3,39,53,73,100,137,151,156,177],"information":[4],"through":[5,142],"social":[6],"media":[7],"and":[8,107],"the":[9,45,51,71,98,145,152,160,178,186,191],"Internet":[10],"has":[11,43,81],"posed":[12],"a":[13,36,120],"significant":[14],"challenge":[15,42],"for":[16,132],"fact-checking,":[17],"among":[18],"others":[19],"in":[20,65,68,86,185,190],"identifying":[21],"check-worthy":[22,112],"claims":[23,32,57],"that":[24,167],"fact-checkers":[25],"should":[26],"pay":[27],"attention":[28,85],"to,":[29],"i.e.":[30],"filtering":[31],"needing":[33],"fact-checking":[34],"from":[35,114],"large":[37,74],"pool":[38],"sentences.":[40],"This":[41],"stressed":[44],"need":[46],"to":[47,60,110,125],"focus":[48],"on":[49,144],"determining":[50],"priority":[52],"claims,":[54],"specifically":[55],"which":[56],"are":[58],"worth":[59],"be":[61,171],"fact-checked.":[62],"Despite":[63],"advancements":[64],"this":[66,95],"area":[67],"recent":[69],"years,":[70],"application":[72,99],"language":[75,147],"models":[76],"(LLMs),":[77],"such":[78],"as":[79,149],"GPT,":[80],"only":[82,174],"recently":[83],"drawn":[84],"studies.":[87],"However,":[88],"many":[89],"open-source":[90,103],"LLMs":[91,104],"remain":[92],"underexplored.":[93],"Therefore,":[94],"study":[96],"investigates":[97],"eight":[101],"prominent":[102],"with":[105,163,173],"fine-tuning":[106],"prompt":[108],"engineering":[109],"identify":[111,127],"statements":[113],"political":[115],"transcriptions.":[116],"Further,":[117,159],"we":[118],"propose":[119],"two-step":[121],"data":[122,130,164],"pruning":[123,165],"approach":[124,139],"automatically":[126],"high-quality":[128],"training":[129,179],"instances":[131],"effective":[133],"learning.":[134],"efficiency":[136],"our":[138],"is":[140],"demonstrated":[141],"evaluations":[143],"English":[146,192],"dataset":[148],"part":[150],"check-worthiness":[153,187],"estimation":[154,188],"task":[155,189],"CheckThat!":[157],"2024.":[158],"experiments":[161],"conducted":[162],"demonstrate":[166],"competitive":[168],"performance":[169],"can":[170],"achieved":[172],"about":[175],"44\\%":[176],"data.":[180],"Our":[181],"team":[182],"ranked":[183],"first":[184],"language.":[193]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2024-06-28T00:00:00"}