{"id":3965,"date":"2023-10-24T03:42:00","date_gmt":"2023-10-23T18:42:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=3965"},"modified":"2023-10-24T03:42:00","modified_gmt":"2023-10-23T18:42:00","slug":"automatic-hallucination-assessment-for-aligned-large-language-models-via-transferable-adversarial-attacks","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=3965","title":{"rendered":"Automatic Hallucination Assessment for Aligned Large Language Models via Transferable Adversarial Attacks"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Automatic Hallucination Assessment for Aligned Large Language Models via Transferable Adversarial Attacks\u00a0<\/strong>[98.2]<br>\u672c\u7a3f\u3067\u306f,\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb\u304c\u5fe0\u5b9f\u306b\u632f\u308b\u821e\u3046\u65e2\u5b58\u30c7\u30fc\u30bf\u3092\u9069\u5207\u306b\u4fee\u6b63\u3057,\u8a55\u4fa1\u30c7\u30fc\u30bf\u3092\u81ea\u52d5\u7684\u306b\u751f\u6210\u3059\u308b\u624b\u6cd5\u3092\u958b\u767a\u3059\u308b\u3053\u3068\u3092\u76ee\u7684\u3068\u3059\u308b\u3002 \u5177\u4f53\u7684\u306b\u306f,LLM \u30d9\u30fc\u30b9\u306e\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3042\u308b Auto Debug \u306b\u3064\u3044\u3066\u8ff0\u3079\u308b\u3002 \u5b9f\u9a13\u7d50\u679c\u304b\u3089, LLM\u306f, \u30a4\u30f3\u30d7\u30ed\u30f3\u30d7\u30c8\u306b\u4e0e\u3048\u3089\u308c\u305f\u77e5\u8b58\u3068\u30d1\u30e9\u30e1\u30c8\u30ea\u30c3\u30af\u77e5\u8b58\u3068\u306e\u9593\u306b\u77db\u76fe\u304c\u3042\u308b\u5834\u5408, \u8cea\u554f\u5fdc\u7b54\u30b7\u30ca\u30ea\u30aa\u306e2\u3064\u306e\u30ab\u30c6\u30b4\u30ea\u306b\u5e7b\u899a\u3092\u4e0e\u3048\u308b\u53ef\u80fd\u6027\u304c\u793a\u5506\u3055\u308c\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2310.12516v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2310.12516v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 19 Oct 2023 06:37:32 GMT)<\/li>\n\n\n\n<li>LLM\u3092\u8a55\u4fa1\u3059\u308b\u305f\u3081\uff08\u306bHallucination\u3092\u5f15\u304d\u8d77\u3053\u3059\uff09\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u30a8\u30d3\u30c7\u30f3\u30b9\u4ed8\u304d\u3067\u81ea\u52d5\u4f5c\u6210\u3059\u308bAutoDebug\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u30ef\u30fc\u30af\u306e\u63d0\u6848\u3001\u5bfeGPT-4\u3084PaLM\u306b\u5bfe\u3057\u3066\u3082\u6709\u52b9\u306a\u3088\u3046<\/li>\n\n\n\n<li>\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30b5\u30a4\u30c8\u306f<a href=\"https:\/\/autodebug-llm.github.io\/\">Automatic Hallucination Assessment for Aligned Large Language Models via Transferable Adversarial Attacks (autodebug-llm.github.io)<\/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":[184,223],"class_list":["post-3965","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-hallucination","tag-llm"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3965","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=3965"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3965\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3965"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3965"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3965"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}