Jul 2026
MEDit-Bench: A Dataset for Evaluating Message-Driven Narrative Video Editing
An automatic evaluation protocol based on temporal alignment metrics is defined, and it is found that an LLM-as-a-judge preference, a natural proxy for narrative quality, is unreliable for this task due to severe position bias.
K. Ogata, Zongshang Pang, Mayu Otani et al.
· arXiv.org · 1 citation