{"id":3583,"date":"2023-07-20T06:32:00","date_gmt":"2023-07-19T21:32:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=3583"},"modified":"2023-07-20T06:32:00","modified_gmt":"2023-07-19T21:32:00","slug":"ethicist-extraction-through-loss-smoothed-soft-prompting-and-calibrated-confidence-estimationethicist","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=3583","title":{"rendered":"ETHICIST: \u00a0Extraction THrough loss smoothed soft prompting and calIbrated ConfIdence eSTimationETHICIST:"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation\u00a0<\/strong>[56.6]<br>\u672c\u7814\u7a76\u3067\u306f,\u5bfe\u8c61\u3068\u3059\u308b\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30c7\u30fc\u30bf\u62bd\u51fa\u306e\u305f\u3081\u306eEthicist\u3068\u3044\u3046\u624b\u6cd5\u3092\u63d0\u6848\u3059\u308b\u3002 \u30e1\u30e2\u30ea\u5316\u3092\u8a98\u767a\u3059\u308b\u305f\u3081\u3001\u30e2\u30c7\u30eb\u3092\u56fa\u5b9a\u3057\u306a\u304c\u3089\u30bd\u30d5\u30c8\u306a\u30d7\u30ed\u30f3\u30d7\u30c8\u57cb\u3081\u8fbc\u307f\u3092\u30c1\u30e5\u30fc\u30cb\u30f3\u30b0\u3059\u308b\u3002 \u6211\u3005\u306f,\u6700\u8fd1\u63d0\u6848\u3055\u308c\u305f\u516c\u958b\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u306b\u304a\u3044\u3066,\u30a8\u30c6\u30a3\u30b7\u30b9\u30c8\u304c\u62bd\u51fa\u6027\u80fd\u3092\u8457\u3057\u304f\u5411\u4e0a\u3059\u308b\u3053\u3068\u3092\u793a\u3059\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2307.04401v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2307.04401v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Mon, 10 Jul 2023 08:03:41 GMT)<\/li>\n\n\n\n<li>\u5b66\u7fd2\u30c7\u30fc\u30bf\u3092\u62bd\u51fa\u3059\u308b\u624b\u6cd5\u306e\u63d0\u6848\u3001<a href=\"https:\/\/github.com\/google-research\/lm-extraction-benchmark\">GitHub &#8211; google-research\/lm-extraction-benchmark<\/a>\u3067\u52b9\u679c\u3092\u78ba\u8a8d\u3068\u306e\u3053\u3068\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/thu-coai\/Targeted-Data-Extraction\">GitHub &#8211; thu-coai\/Targeted-Data-Extraction: Official Code for ACL 2023 paper: &#8220;Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation&#8221;<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[32,223],"class_list":["post-3583","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-attack","tag-llm"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3583","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=3583"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3583\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3583"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3583"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3583"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}