{"id":5130,"date":"2024-07-08T05:36:00","date_gmt":"2024-07-07T20:36:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5130"},"modified":"2024-07-08T05:36:00","modified_gmt":"2024-07-07T20:36:00","slug":"mirai-evaluating-llm-agents-for-event-forecasting","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5130","title":{"rendered":"MIRAI: Evaluating LLM Agents for Event Forecasting"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>MIRAI: Evaluating LLM Agents for Event Forecasting\u00a0<\/strong>[22.5]<br>\u6211\u3005\u306f,\u56fd\u969b\u30a4\u30d9\u30f3\u30c8\u306e\u6587\u8108\u306b\u304a\u3044\u3066,LLM\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u3092\u6642\u9593\u4e88\u6e2c\u5668\u3068\u3057\u3066\u8a55\u4fa1\u3059\u308b\u305f\u3081\u306e\u65b0\u3057\u3044\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u3042\u308bMIRAI\u3092\u7d39\u4ecb\u3059\u308b\u3002 \u672c\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u306f,\u6b74\u53f2\u7684,\u69cb\u9020\u5316\u3055\u308c\u305f\u30a4\u30d9\u30f3\u30c8\u3084\u30c6\u30ad\u30b9\u30c8\u30cb\u30e5\u30fc\u30b9\u8a18\u4e8b\u306e\u5e83\u7bc4\u306a\u30c7\u30fc\u30bf\u30d9\u30fc\u30b9\u306b\u30a2\u30af\u30bb\u30b9\u3059\u308b\u305f\u3081\u306e\u30c4\u30fc\u30eb\u3092\u5099\u3048\u305f\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u74b0\u5883\u3092\u7279\u5fb4\u3068\u3059\u308b\u3002 \u307e\u3068\u3081\u308b\u3068\u3001MIRAI\u306f\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u306e\u80fd\u529b\u30923\u3064\u306e\u6b21\u5143\u3067\u7dcf\u5408\u7684\u306b\u8a55\u4fa1\u3059\u308b\u30021) \u5927\u898f\u6a21\u30b0\u30ed\u30fc\u30d0\u30eb\u30c7\u30fc\u30bf\u30d9\u30fc\u30b9\u304b\u3089\u91cd\u8981\u306a\u60c5\u5831\u3092\u81ea\u5f8b\u7684\u306b\u30bd\u30fc\u30b9\u3057\u7d71\u5408\u3059\u308b\u3053\u3068\u30012) \u30c9\u30e1\u30a4\u30f3\u56fa\u6709\u306eAPI\u3068\u30c4\u30fc\u30eb\u4f7f\u7528\u306e\u305f\u3081\u306e\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u4f7f\u3063\u3066\u30b3\u30fc\u30c9\u3092\u66f8\u304f\u3053\u3068\u30013) \u591a\u69d8\u306a\u30d5\u30a9\u30fc\u30de\u30c3\u30c8\u3084\u6642\u9593\u304b\u3089\u6b74\u53f2\u7684\u77e5\u8b58\u3092\u5171\u540c\u3067\u5f15\u304d\u7d99\u304e\u3001\u5c06\u6765\u7684\u306a\u4e8b\u8c61\u3092\u6b63\u78ba\u306b\u4e88\u6e2c\u3059\u308b\u3053\u3068\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2407.01231v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2407.01231v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Mon, 01 Jul 2024 12:22:46 GMT)<\/li>\n\n\n\n<li>AI\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u304c\u672a\u6765\u3092\u4e88\u6e2c\u3067\u304d\u308b\u304b\u3092\u6e2c\u308b\u305f\u3081\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3002\u300cWe finalized a collection of 991,759 GDELT event records, corresponding to 59,161 unique events and 296,630 unique news articles. Our test set contains 705 query and answer pairs on forecasting an event of given timestamp between two countries, with a 100 balanced test subset.\u300d\uff08GDELT=<a href=\"https:\/\/www.gdeltproject.org\/\">The GDELT Project<\/a>\uff09\u3068\u5927\u898f\u6a21\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/mirai-llm.github.io\/\">MIRAI: Evaluating LLM Agents for Event Forecasting (mirai-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":[42,223],"class_list":["post-5130","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-autonomous-agent","tag-llm"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5130","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=5130"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5130\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5130"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5130"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5130"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}