Saved in:
Bibliographic Details
Main Authors: Zhang, Yue, Zuo, Jingxuan, Su, Ke, Jing, Liqiang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.11414
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911288805818368
author Zhang, Yue
Zuo, Jingxuan
Su, Ke
Jing, Liqiang
author_facet Zhang, Yue
Zuo, Jingxuan
Su, Ke
Jing, Liqiang
contents Multimodal summarization aims to generate a concise summary based on the input text and image. However, the existing methods potentially suffer from unfactual output. To evaluate the factuality of multimodal summarization models, we propose two fine-grained and explainable evaluation frameworks (FALLACIOUS) for different application scenarios, i.e. reference-based factuality evaluation framework and reference-free factuality evaluation framework. Notably, the reference-free factuality evaluation framework doesn't need ground truth and hence it has a wider application scenario. To evaluate the effectiveness of the proposed frameworks, we compute the correlation between our frameworks and the other metrics. The experimental results show the effectiveness of our proposed method. We will release our code and dataset via github.
format Preprint
id arxiv_https___arxiv_org_abs_2402_11414
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Fine-grained and Explainable Factuality Evaluation for Multimodal Summarization
Zhang, Yue
Zuo, Jingxuan
Su, Ke
Jing, Liqiang
Computation and Language
Multimodal summarization aims to generate a concise summary based on the input text and image. However, the existing methods potentially suffer from unfactual output. To evaluate the factuality of multimodal summarization models, we propose two fine-grained and explainable evaluation frameworks (FALLACIOUS) for different application scenarios, i.e. reference-based factuality evaluation framework and reference-free factuality evaluation framework. Notably, the reference-free factuality evaluation framework doesn't need ground truth and hence it has a wider application scenario. To evaluate the effectiveness of the proposed frameworks, we compute the correlation between our frameworks and the other metrics. The experimental results show the effectiveness of our proposed method. We will release our code and dataset via github.
title Fine-grained and Explainable Factuality Evaluation for Multimodal Summarization
topic Computation and Language
url https://arxiv.org/abs/2402.11414