{"id":"https://openalex.org/W4416035670","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1295","title":"Refining Attention for Explainable and Noise-Robust Fact-Checking with Transformers","display_name":"Refining Attention for Explainable and Noise-Robust Fact-Checking with Transformers","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035670","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1295"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1295","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1295","pdf_url":"https://aclanthology.org/2025.emnlp-main.1295.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1295.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093471806","display_name":"Jean-Flavien Bussotti","orcid":null},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Jean-Flavien Bussotti","raw_affiliation_strings":["Megagon Labs , USA EURECOM , France","Eurecom [Sophia Antipolis] (Campus SophiaTech, 450 Route des Chappes, CS 50193 - 06904 Biot Sophia Antipolis cedex - France)"],"affiliations":[{"raw_affiliation_string":"Megagon Labs , USA EURECOM , France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"Eurecom [Sophia Antipolis] (Campus SophiaTech, 450 Route des Chappes, CS 50193 - 06904 Biot Sophia Antipolis cedex - France)","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011336242","display_name":"Paolo Papotti","orcid":"https://orcid.org/0000-0003-0651-4128"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Paolo Papotti","raw_affiliation_strings":["Megagon Labs , USA EURECOM , France","Eurecom [Sophia Antipolis] (Campus SophiaTech, 450 Route des Chappes, CS 50193 - 06904 Biot Sophia Antipolis cedex - France)"],"affiliations":[{"raw_affiliation_string":"Megagon Labs , USA EURECOM , France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"Eurecom [Sophia Antipolis] (Campus SophiaTech, 450 Route des Chappes, CS 50193 - 06904 Biot Sophia Antipolis cedex - France)","institution_ids":["https://openalex.org/I1902872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5093471806"],"corresponding_institution_ids":["https://openalex.org/I1902872"],"apc_list":null,"apc_paid":null,"fwci":2.3431,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91711922,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"25487","last_page":"25499"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.8287000060081482,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.8287000060081482,"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":0.034699998795986176,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.012799999676644802,"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/refining","display_name":"Refining (metallurgy)","score":0.6028000116348267},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5670999884605408},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.2662999927997589},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.22429999709129333}],"concepts":[{"id":"https://openalex.org/C60044698","wikidata":"https://www.wikidata.org/wiki/Q1283324","display_name":"Refining (metallurgy)","level":2,"score":0.6028000116348267},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5670999884605408},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4884999990463257},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.46209999918937683},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.27070000767707825},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.24699999392032623},{"id":"https://openalex.org/C117671659","wikidata":"https://www.wikidata.org/wiki/Q11049265","display_name":"Manufacturing engineering","level":1,"score":0.24140000343322754},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.22429999709129333},{"id":"https://openalex.org/C101382669","wikidata":"https://www.wikidata.org/wiki/Q1616769","display_name":"Ferroresonance in electricity networks","level":4,"score":0.22030000388622284}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1295","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1295","pdf_url":"https://aclanthology.org/2025.emnlp-main.1295.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05401184v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05401184","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EMNLP 2025, 30th Conference on Empirical Methods in Natural Language Processing, Nov 2025, Suzhou, China","raw_type":"Conference papers"},{"id":"pmh:oai:fr.eurecom:8414","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196942","display_name":"Graduate School and Research Center in Digital Science (EURECOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1902872","host_organization_name":"EURECOM","host_organization_lineage":["https://openalex.org/I1902872"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EMNLP 2025, 30th Conference on Empirical Methods in Natural Language Processing, 4-9 November 2025, Suzhou, China","raw_type":"Poster / Demo"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1295","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1295","pdf_url":"https://aclanthology.org/2025.emnlp-main.1295.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4622970671","display_name":null,"funder_award_id":"ANR-23-IACL-0001","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5891368634","display_name":null,"funder_award_id":"ANR-21-CE23-0037","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035670.pdf","grobid_xml":"https://content.openalex.org/works/W4416035670.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"tasks":[1],"like":[2],"question":[3,108],"answering":[4],"and":[5,35,58,84,103,123],"factchecking,":[6],"models":[7,20],"must":[8],"discern":[9],"relevant":[10,89,121],"information":[11],"from":[12],"extensive":[13],"corpora":[14],"in":[15,107,116,129],"an":[16],"\"openbook\"":[17],"setting.Conventional":[18],"transformer-based":[19],"excel":[21],"at":[22],"classifying":[23],"input":[24,92],"data,":[25],"but":[26],"(i)":[27],"often":[28],"falter":[29],"due":[30],"to":[31,33,54,60,81,85,114,127],"sensitivity":[32],"noise":[34,61],"(ii)":[36],"lack":[37],"explainability":[38],"regarding":[39],"their":[40],"decision":[41],"process.To":[42],"address":[43],"these":[44],"challenges,":[45],"we":[46],"introduce":[47],"ATTUN,":[48],"a":[49,69,136],"novel":[50],"transformer":[51],"architecture":[52],"designed":[53],"enhance":[55],"model":[56,79],"transparency":[57],"resilience":[59],"by":[62],"refining":[63],"the":[64,78,87],"attention":[65,75],"mechanisms.Our":[66],"approach":[67],"involves":[68],"dedicated":[70],"module":[71],"that":[72],"directly":[73],"modifies":[74],"weights,":[76],"allowing":[77],"both":[80],"improve":[82],"predictions":[83],"identify":[86],"most":[88],"sections":[90],"of":[91,112,125],"data":[93],"after":[94],"supervised":[95],"training.We":[96],"validate":[97],"our":[98],"methodology":[99],"using":[100],"fact-checking":[101],"datasets":[102],"show":[104],"promising":[105],"results":[106],"answering.Experiments":[109],"demonstrate":[110],"improvements":[111],"up":[113,126],"51%":[115],"F1":[117],"score":[118],"for":[119],"detecting":[120],"context,":[122],"gains":[124],"18%":[128],"task":[130],"accuracy":[131],"when":[132],"integrating":[133],"ATTUN":[134],"into":[135],"model.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-11-08T00:00:00"}