Year: 2025
Type: conference-paper
Abstract: Recent advances in large language models and vision-language models have led to growing interest in explainable evaluation metrics for image captioning.However, these metrics generate explanations without standardized criteria, and the overall quality of the generated explanations remains unverified.In this paper, we propose EXPERT, a reference-free evaluation metric that provides structured explanations based on three fundamental criteria: fluency, relevance, and descriptiveness.By constructing large-scale datasets of highquality structured explanations, we develop a two-stage evaluation template to effectively supervise a vision-language model for both scoring and explanation generation.EXPERT achieves state-of-the-art results on benchmark datasets while providing significantly higherquality explanations than existing metrics, as validated through comprehensive human evaluation.Our code and datasets are available at https://github.com/hjkim811/EXPERT.
Authors: Hyunjong Kim, Sangyeop Kim, Jongheon Jeong, Yeongjae Cho, Sungzoon Cho
Institution: Seoul National University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Awards: G1251031942, G2511445776, G30685149
OpenAlex ID: W4412944495