arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.13089cs.AIcs.CL
收藏

MetaSumPerceiver:用于事实核查的多模态多文档证据摘要

MetaSumPerceiver: Multimodal Multi-Document Evidence Summarization for Fact-Checking

Virginia Tech(弗吉尼亚理工大学)

Ting-Chih Chen, Chia-Wei Tang, Chris Thomas

AI总结:

本文提出MetaSumPerceiver,一种基于动态感知器的多模态多文档摘要模型,利用强化学习蕴含目标生成区分真实性标签的证据摘要,在MOCHEG数据集上比最先进方法提升4.6%,并在新数据集上表现强劲。

摘要:

核查现实世界中的主张通常需要审阅多个多模态文档以评估主张的真实性,这是一项极其费力且耗时的任务。在本文中,我们提出了一种摘要模型,旨在从多模态、多文档数据集中生成对事实核查有用的、针对特定主张的摘要。该模型以文档、图像和主张作为输入,目标是辅助事实核查任务。我们引入了一种基于动态感知器的模型,能够处理任意长度的多模态输入。为了训练我们的模型,我们利用一种新颖的基于强化学习的蕴含目标来生成摘要,该摘要提供区分不同真实性标签的证据。为了评估我们方法的有效性,我们在现有基准和我们贡献的一个新的多文档主张数据集上进行了实验。我们的方法在MOCHEG数据集上的主张验证任务中比最先进的方法高出4.6%,并在我们新的Multi-News-Fact-Checking数据集上展示了强劲的性能。

英文摘要:

Fact-checking real-world claims often requires reviewing multiple multimodal documents to assess a claim's truthfulness, which is a highly laborious and time-consuming task. In this paper, we present a summarization model designed to generate claim-specific summaries useful for fact-checking from multimodal, multi-document datasets. The model takes inputs in the form of documents, images, and a claim, with the objective of assisting in fact-checking tasks. We introduce a dynamic perceiver-based model that can handle inputs from multiple modalities of arbitrary lengths. To train our model, we leverage a novel reinforcement learning-based entailment objective to generate summaries that provide evidence distinguishing between different truthfulness labels. To assess the efficacy of our approach, we conduct experiments on both an existing benchmark and a new dataset of multi-document claims that we contribute. Our approach outperforms the SOTA approach by 4.6% in the claim verification task on the MOCHEG dataset and demonstrates strong performance on our new Multi-News-Fact-Checking dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑