ML-Promise: A Multilingual Dataset for Corporate Promise Verification

TL;DR

This paper introduces ML-Promise, a multilingual dataset designed to improve verification of corporate promises across languages, focusing on ESG commitments and greenwashing, with promising baseline results using retrieval-augmented generation methods.

Contribution

It presents the first multilingual dataset for promise verification, covering five languages and including textual and image-based data, to advance research in corporate accountability and ESG evaluation.

Findings

Promising results from retrieval-augmented generation approaches.

The dataset enables cross-lingual promise verification research.

Baseline models show potential in assessing promise credibility.

Abstract

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.