{"created":"2025-01-19T01:37:06.647320+00:00","updated":"2025-01-19T09:36:32.637571+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00235109","sets":["1164:4179:11560:11676"]},"path":["11676"],"owner":"44499","recid":"235109","title":["Towards a Benchmark Dataset for Stress-testing Fallacy Detection Models"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-06-21"},"_buckets":{"deposit":"2810756f-3d8e-4960-9e94-33329610c98a"},"_deposit":{"id":"235109","pid":{"type":"depid","value":"235109","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Towards a Benchmark Dataset for Stress-testing Fallacy Detection Models","author_link":["641909","641914","641924","641923","641922","641921","641908","641916","641918","641925","641912","641910","641919","641913","641917","641911","641915","641920"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Towards a Benchmark Dataset for Stress-testing Fallacy Detection Models"},{"subitem_title":"Towards a Benchmark Dataset for Stress-testing Fallacy Detection Models","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"言語資源 (2) ","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2024-06-21","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Japan Advanced Institute of Science and Technology"},{"subitem_text_value":"Beyond Reason"},{"subitem_text_value":"Japan Advanced Institute of Science and Technology／RIKEN"},{"subitem_text_value":"Japan Advanced Institute of Science and Technology"},{"subitem_text_value":"Insa Lyon"},{"subitem_text_value":"Tohoku University"},{"subitem_text_value":"Ricoh Company, Ltd."},{"subitem_text_value":"RIKEN"},{"subitem_text_value":"Mohamed bin Zayed University of Artificial Intelligence／RIKEN／Tohoku University"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Japan Advanced Institute of Science and Technology","subitem_text_language":"en"},{"subitem_text_value":"Beyond Reason","subitem_text_language":"en"},{"subitem_text_value":"Japan Advanced Institute of Science and Technology / RIKEN","subitem_text_language":"en"},{"subitem_text_value":"Japan Advanced Institute of Science and Technology","subitem_text_language":"en"},{"subitem_text_value":"Insa Lyon","subitem_text_language":"en"},{"subitem_text_value":"Tohoku University","subitem_text_language":"en"},{"subitem_text_value":"Ricoh Company, Ltd.","subitem_text_language":"en"},{"subitem_text_value":"RIKEN","subitem_text_language":"en"},{"subitem_text_value":"Mohamed bin Zayed University of Artificial Intelligence / RIKEN / Tohoku University","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/235109/files/IPSJ-NL24260018.pdf","label":"IPSJ-NL24260018.pdf"},"date":[{"dateType":"Available","dateValue":"2026-06-21"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-NL24260018.pdf","filesize":[{"value":"1.3 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"23"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"343d97e9-eed9-42a3-897d-193c92190ce5","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Surawat, Pothong"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Paul, Reisert"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Naoya, Inoue"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Irfan, Robbani"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"CaméLia, Guerraoui"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Wenzhi, Wang"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shoichi, Naito"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Jungmin, Choi"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kentaro, Inui"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Surawat, Pothong","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Paul, Reisert","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Naoya, Inoue","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Irfan, Robbani","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"CaméLia, Guerraoui","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Wenzhi, Wang","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shoichi, Naito","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Jungmin, Choi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kentaro, Inui","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10115061","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8779","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"Arguments with logical fallacies are common in daily discourse. While several benchmark datasets for automated fallacy detection exist [1], none are specifically designed for stress-testing models' ability to assess the validity of underlying logic in the arguments. To address this issue, inspired by the Winograd Schema Challenge, we introduce a pilot benchmark dataset for fallacy detection. Our dataset consists of minimally different pairs of arguments that differ only in their degree of fallaciousness. We report the results of a pilot annotation study and preliminary experiments with large language models. Finally, we discuss potential future directions.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Arguments with logical fallacies are common in daily discourse. While several benchmark datasets for automated fallacy detection exist [1], none are specifically designed for stress-testing models' ability to assess the validity of underlying logic in the arguments. To address this issue, inspired by the Winograd Schema Challenge, we introduce a pilot benchmark dataset for fallacy detection. Our dataset consists of minimally different pairs of arguments that differ only in their degree of fallaciousness. We report the results of a pilot annotation study and preliminary experiments with large language models. Finally, we discuss potential future directions.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告自然言語処理（NL）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2024-06-21","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"18","bibliographicVolumeNumber":"2024-NL-260"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":235109,"links":{}}