{"id":8073,"date":"2026-01-20T05:26:00","date_gmt":"2026-01-19T20:26:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=8073"},"modified":"2026-01-11T14:30:30","modified_gmt":"2026-01-11T05:30:30","slug":"all-that-glisters-is-not-gold-a-benchmark-for-reference-free-counterfactual-financial-misinformation-detection","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=8073","title":{"rendered":"All That Glisters Is Not Gold: A Benchmark for Reference-Free Counterfactual Financial Misinformation Detection\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>All That Glisters Is Not Gold: A Benchmark for Reference-Free Counterfactual Financial Misinformation Detection\u00a0<\/strong>[67.9]<br>RFC Bench\u306f\u3001\u73fe\u5b9f\u7684\u306a\u30cb\u30e5\u30fc\u30b9\u306e\u4e0b\u3067\u8ca1\u52d9\u7684\u306a\u8aa4\u60c5\u5831\u306b\u95a2\u3059\u308b\u5927\u898f\u6a21\u306a\u8a00\u8a9e\u30e2\u30c7\u30eb\u3092\u8a55\u4fa1\u3059\u308b\u305f\u3081\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u3042\u308b\u3002 \u3053\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u306f\u30012\u3064\u306e\u88dc\u5b8c\u7684\u306a\u30bf\u30b9\u30af\u304c\u5b9a\u7fa9\u3055\u308c\u3066\u3044\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2601.04160v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2601.04160v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Wed, 07 Jan 2026 18:18:28 GMT)<\/li>\n\n\n\n<li>\u91d1\u878d\u306e\u8aa4\u60c5\u5831\u691c\u77e5\u3092\u76ee\u6307\u3057\u305f\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3002\u300cThe benchmark defines two complementary tasks: reference-free misinformation detection and comparison-based diagnosis using paired original\u2013perturbed inputs. Experiments reveal a consistent pattern: performance is substantially stronger when comparative con- text is available, while reference-free settings expose significant weaknesses, including un- stable predictions and elevated invalid outputs.<br>These results indicate that current models struggle to maintain coherent belief states without external grounding. By highlighting this gap, RFC-BENCH provides a structured testbed for studying reference-free reasoning and advancing more reliable financial misinformation detection in real-world settings.\u300d<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/lzw108\/FMD\">GitHub &#8211; lzw108\/FMD: This is a continuous project on Financial Misinformation Detection (FMD).<\/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":[517,665],"class_list":["post-8073","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-517","tag-665"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/8073","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=8073"}],"version-history":[{"count":1,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/8073\/revisions"}],"predecessor-version":[{"id":8074,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/8073\/revisions\/8074"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=8073"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=8073"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=8073"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}