{"id":6822,"date":"2025-05-27T02:55:00","date_gmt":"2025-05-26T17:55:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6822"},"modified":"2025-05-25T09:57:30","modified_gmt":"2025-05-25T00:57:30","slug":"chartmuseum-testing-visual-reasoning-capabilities-of-large-vision-language-models","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6822","title":{"rendered":"ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models\u00a0<\/strong>[37.5]<br>\u8996\u899a\u7684\u63a8\u8ad6\u306b\u3088\u3063\u3066\u306e\u307f\u89e3\u6c7a\u53ef\u80fd\u306a\u5408\u6210\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u7528\u3044\u3066\u30b1\u30fc\u30b9\u30b9\u30bf\u30c7\u30a3\u3092\u884c\u3046\u3002 \u6b21\u306b\u30011,162\u4eba\u306e\u5c02\u9580\u5bb6\u304c\u6ce8\u91c8\u3092\u4ed8\u3051\u305f\u8cea\u554f\u3092\u542b\u3080\u65b0\u3057\u3044\u30c1\u30e3\u30fc\u30c8\u8cea\u554f\u56de\u7b54(QA)\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u3042\u308bChartMuseum\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002 \u4eba\u9593\u306f93%\u306e\u7cbe\u5ea6\u3092\u9054\u6210\u3057\u3066\u3044\u308b\u304c\u3001\u6700\u9ad8\u306e\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u30e2\u30c7\u30eb\u3067\u3042\u308bGemini-2.5-Pro\u306f63.0%\u3057\u304b\u9054\u6210\u3067\u304d\u305a\u3001\u4e3b\u8981\u306a\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u3067\u3042\u308bLVLM Qwen2.5-VL-72B-Instruct\u306f38.5%\u3057\u304b\u9054\u6210\u3057\u3066\u3044\u306a\u3044\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2505.13444v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2505.13444v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Mon, 19 May 2025 17:59:27 GMT)<\/li>\n\n\n\n<li>\u30c1\u30e3\u30fc\u30c8QA\u306a\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3002Gemini-2.5-Pro\u3001o4, o3, Calude 3.7, GPT-4.1\u3082\u30b9\u30b3\u30a2\u304c\u4f4e\u3044\u56f0\u96e3\u306a\u30bf\u30b9\u30af\u3002<\/li>\n\n\n\n<li>\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30b5\u30a4\u30c8\u306f<a href=\"https:\/\/chartmuseum-leaderboard.github.io\/\">ChartMuseum<\/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":[489,491],"class_list":["post-6822","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-489","tag-491"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6822","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=6822"}],"version-history":[{"count":1,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6822\/revisions"}],"predecessor-version":[{"id":6823,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6822\/revisions\/6823"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6822"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6822"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6822"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}