arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2411.04473cs.CL
收藏

ML-Promise:用于企业承诺验证的多语言数据集

ML-Promise: A Multilingual Dataset for Corporate Promise Verification

Institute of Library, Information, and Media Science, University of Tsukuba(筑波大学图书馆、信息与媒体科学研究所);College of Knowledge and Library Sciences, School of Informatics, University of Tsukuba(筑波大学信息学研究科知识与图书馆学学院);DS Outscale(3DS Outscale公司);Shinhan Securities Co.(新韩证券公司);Graduate Institute of Information Management, National Taipei University(国立台北大学资讯管理研究所);AIST(日本产业技术综合研究所)

Yohei Seki, Hakusen Shu, Anaïs Lhuissier, Hanwool Lee, Juyeon Kang, Min-Yuh Day, Chung-Chi Chen

AI总结:

本文提出首个多语言数据集ML-Promise,涵盖五种语言,用于系统验证企业承诺,特别是在ESG报告中,并通过检索增强生成方法取得良好效果。

摘要:

政客、企业领袖和公众人物所作的承诺对公众认知、信任和机构声誉具有显著影响。然而,此类承诺的复杂性和数量,加之验证其履行情况的困难,亟需创新方法来评估其可信度。本文引入了承诺验证(Promise Verification)的概念,这是一种系统性的方法,涉及承诺识别、证据评估和验证时机评估等步骤。我们提出了首个多语言数据集ML-Promise,涵盖英语、法语、中文、日语和韩语,旨在促进对承诺的深入验证,特别是在环境、社会和治理(ESG)报告的背景下。鉴于对企业环境贡献的日益重视,该数据集解决了评估企业承诺的挑战,尤其是考虑到漂绿(greenwashing)等做法。我们的研究还探索了基于文本和图像的基线方法,其中检索增强生成(RAG)方法取得了有前景的结果。这项工作旨在促进跨多种语言和领域对公共承诺问责制的进一步讨论。

英文摘要:

Promises made by politicians, corporate leaders, and public figures have a significant impact on public perception, trust, and institutional reputation. However, the complexity and volume of such commitments, coupled with difficulties in verifying their fulfillment, necessitate innovative methods for assessing their credibility. This paper introduces the concept of Promise Verification, a systematic approach involving steps such as promise identification, evidence assessment, and the evaluation of timing for verification. We propose the first multilingual dataset, ML-Promise, which includes English, French, Chinese, Japanese, and Korean, aimed at facilitating in-depth verification of promises, particularly in the context of Environmental, Social, and Governance (ESG) reports. Given the growing emphasis on corporate environmental contributions, this dataset addresses the challenge of evaluating corporate promises, especially in light of practices like greenwashing. Our findings also explore textual and image-based baselines, with promising results from retrieval-augmented generation (RAG) approaches. This work aims to foster further discourse on the accountability of public commitments across multiple languages and domains.

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。

↑