ML-Promise: A Multilingual Dataset for Corporate Promise Verification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Seki, Yohei, Shu, Hakusen, Lhuissier, Anaïs, Lee, Hanwool, Kang, Juyeon, Day, Min-Yuh, Chen, Chung-Chi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929580845039616
author Seki, Yohei
Shu, Hakusen
Lhuissier, Anaïs
Lee, Hanwool
Kang, Juyeon
Day, Min-Yuh
Chen, Chung-Chi
author_facet Seki, Yohei
Shu, Hakusen
Lhuissier, Anaïs
Lee, Hanwool
Kang, Juyeon
Day, Min-Yuh
Chen, Chung-Chi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_04473
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ML-Promise: A Multilingual Dataset for Corporate Promise Verification
Seki, Yohei
Shu, Hakusen
Lhuissier, Anaïs
Lee, Hanwool
Kang, Juyeon
Day, Min-Yuh
Chen, Chung-Chi
Computation and Language
I.2.7
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.
title ML-Promise: A Multilingual Dataset for Corporate Promise Verification
topic Computation and Language
I.2.7
url https://arxiv.org/abs/2411.04473