{"id":6646,"date":"2026-09-25T15:00:35","date_gmt":"2026-09-25T06:00:35","guid":{"rendered":"https:\/\/www-dsc.naist.jp\/dsc_naist\/?p=6646"},"modified":"2026-08-06T15:05:51","modified_gmt":"2026-08-06T06:05:51","slug":"dsc-internal-talk-in-sept2026","status":"publish","type":"post","link":"https:\/\/www-dsc.naist.jp\/dsc_naist\/en\/dsc-internal-talk-in-sept2026\/","title":{"rendered":"DSC internal talk in September"},"content":{"rendered":"<p>Prof. Taro Watanabe gave a lecture in September.<\/p>\n<p>The details are as follows.<\/p>\n<p>====================<\/p>\n<p>Prof. Taro Watanabe (Natural Language Processing Laboratory)<\/p>\n<p>TITLE:<br \/>\nLanguage Model Knowledge Probing<\/p>\n<p>ABSTRACT\uff1a<\/p>\n<p>Language models have been employed in various knowledge-intensive tasks, like question-answering, and it is critical to investigate the factual knowledge encoded in language models. In this study, we propose an efficient knowledge probing method, DEcoder Embedding-based Relational (DEER), in which both queries and answers are encoded by language model internal representations, allowing efficient inference and robust probing.<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<div class=\"block-list-appender wp-block\" tabindex=\"-1\" contenteditable=\"false\" data-block=\"true\">\n<div class=\"block-editor-default-block-appender\" data-root-client-id=\"\">\n<p class=\"block-editor-default-block-appender__content\" tabindex=\"0\" role=\"button\" aria-label=\"\u30c7\u30d5\u30a9\u30eb\u30c8\u30d6\u30ed\u30c3\u30af\u3092\u8ffd\u52a0\">\u00a0<\/p>\n<\/div>\n<\/div>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Prof. Taro Watanabe gave a lecture in September. The details are as follows. ==================== Prof. Taro Watanabe (Natural Language Processing Laboratory) TITLE: Language Model Knowledge Probing ABSTRACT\uff1a Language models have been employed in various knowledge-intensive tasks, like question-answering, and it is critical to investigate the factual knowledge encoded in language models. In this study, we [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_locale":"en_US","_original_post":"https:\/\/www-dsc.naist.jp\/dsc_naist\/?p=6643","_links_to":"","_links_to_target":""},"categories":[3],"tags":[],"event_taxonomy":[15],"acf":[],"_links":{"self":[{"href":"https:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/posts\/6646"}],"collection":[{"href":"https:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/comments?post=6646"}],"version-history":[{"count":2,"href":"https:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/posts\/6646\/revisions"}],"predecessor-version":[{"id":6648,"href":"https:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/posts\/6646\/revisions\/6648"}],"wp:attachment":[{"href":"https:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/media?parent=6646"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/categories?post=6646"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/tags?post=6646"},{"taxonomy":"event_taxonomy","embeddable":true,"href":"https:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/event_taxonomy?post=6646"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}