Evaluation | Xunyi's Academic Websitehttps://jiangxunyi.github.io/tag/evaluation/EvaluationHugo Blox Builder (https://hugoblox.com)en-usWed, 11 Nov 2026 00:00:00 +0000https://jiangxunyi.github.io/media/icon_hu12864870738162112581.pngEvaluationhttps://jiangxunyi.github.io/tag/evaluation/Evaluating Music Context Preservation: A Multi-facet Framework for Music Editing Systemshttps://jiangxunyi.github.io/publication/musecpbench/Wed, 11 Nov 2026 00:00:00 +0000https://jiangxunyi.github.io/publication/musecpbench/<p>MuseCPBench evaluates whether music editing systems preserve the musical properties that an edit should leave unchanged. It compares editing methods across four groups of musical characteristics and identifies recurring weaknesses in preservation.</p> <p>The linked preprint is titled “MuseCPBench: an Empirical Study of Music Editing Methods through Music Context Preservation.” The title above follows the ISMIR 2026 program.</p>Reasoning Pathologies in Large Language Models: A Diagnostic Perspectivehttps://jiangxunyi.github.io/publication/reasoningpathologies/Tue, 01 Sep 2026 00:00:00 +0000https://jiangxunyi.github.io/publication/reasoningpathologies/<p>A diagnostic study of reasoning failures in large language models.</p>