@inproceedings{huang-etal-2025-multilingual-promise,
title = "Multilingual Promise Verification in {ESG} Reports with Large Language Model Performance Evaluation",
author = "Huang, Wei-Chen and
Lu, Hsin-Ting and
Chen, Wen-Ze and
Day, Min-Yuh",
editor = "Chang, Kai-Wei and
Lu, Ke-Han and
Yang, Chih-Kai and
Tam, Zhi-Rui and
Chang, Wen-Yu and
Wang, Chung-Che",
booktitle = "Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)",
month = nov,
year = "2025",
address = "National Taiwan University, Taipei City, Taiwan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.rocling-main.32/",
pages = "303--313",
ISBN = "979-8-89176-379-1",
abstract = "Corporate ESG reports often contain statements that are vague or difficult to verify, creating room for potential greenwashing. Building automated systems to evaluate such claims is therefore a relevant research direction. Yet, existing analytical tools still show limited ability to verify sustainability promises in multiple languages, especially beyond English. This study examines how large language models (GPT-5) perform in verifying ESG-related promises across Chinese, Japanese, and English reports, aiming to provide a multilingual evaluation baseline. We assess four verification tasks using the PromiseEval datasets [1] in three languages, comparing five prompting strategies from zero-shot to five-shot learning, including Chain-of-Thought reasoning. The four subtasks are Promise Identification (PI), Evidence Status Assessment (ESA), Evidence Quality Evaluation (EQE), and Verification Timeline Prediction (VTP). The five-shot setting achieved the highest overall performance (71.12 {\%} accuracy, 51.92 {\%} Macro-F1). Although the accuracy results appear higher for Chinese (85.12 {\%}) than for Japanese (68.94 {\%}) and English (63.62 {\%}), this mainly reflects class imbalance in the data. Hence, Macro-F1 provides a fairer comparison across languages. Among the four tasks, Evidence Quality Evaluation (EQE) remains the most difficult. While Chain-of-Thought prompting slightly lowers the overall average, it shows selective benefit on the more complex EQE task. Overall, this work offers a clearer multilingual baseline for ESG promise verification and supports the development of language-based tools that enhance the credibility and transparency of sustainability reporting."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2025-multilingual-promise">
<titleInfo>
<title>Multilingual Promise Verification in ESG Reports with Large Language Model Performance Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei-Chen</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Ting</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen-Ze</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yuh</namePart>
<namePart type="family">Day</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ke-Han</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chih-Kai</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhi-Rui</namePart>
<namePart type="family">Tam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen-Yu</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chung-Che</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">National Taiwan University, Taipei City, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-379-1</identifier>
</relatedItem>
<abstract>Corporate ESG reports often contain statements that are vague or difficult to verify, creating room for potential greenwashing. Building automated systems to evaluate such claims is therefore a relevant research direction. Yet, existing analytical tools still show limited ability to verify sustainability promises in multiple languages, especially beyond English. This study examines how large language models (GPT-5) perform in verifying ESG-related promises across Chinese, Japanese, and English reports, aiming to provide a multilingual evaluation baseline. We assess four verification tasks using the PromiseEval datasets [1] in three languages, comparing five prompting strategies from zero-shot to five-shot learning, including Chain-of-Thought reasoning. The four subtasks are Promise Identification (PI), Evidence Status Assessment (ESA), Evidence Quality Evaluation (EQE), and Verification Timeline Prediction (VTP). The five-shot setting achieved the highest overall performance (71.12 % accuracy, 51.92 % Macro-F1). Although the accuracy results appear higher for Chinese (85.12 %) than for Japanese (68.94 %) and English (63.62 %), this mainly reflects class imbalance in the data. Hence, Macro-F1 provides a fairer comparison across languages. Among the four tasks, Evidence Quality Evaluation (EQE) remains the most difficult. While Chain-of-Thought prompting slightly lowers the overall average, it shows selective benefit on the more complex EQE task. Overall, this work offers a clearer multilingual baseline for ESG promise verification and supports the development of language-based tools that enhance the credibility and transparency of sustainability reporting.</abstract>
<identifier type="citekey">huang-etal-2025-multilingual-promise</identifier>
<location>
<url>https://aclanthology.org/2025.rocling-main.32/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>303</start>
<end>313</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual Promise Verification in ESG Reports with Large Language Model Performance Evaluation
%A Huang, Wei-Chen
%A Lu, Hsin-Ting
%A Chen, Wen-Ze
%A Day, Min-Yuh
%Y Chang, Kai-Wei
%Y Lu, Ke-Han
%Y Yang, Chih-Kai
%Y Tam, Zhi-Rui
%Y Chang, Wen-Yu
%Y Wang, Chung-Che
%S Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C National Taiwan University, Taipei City, Taiwan
%@ 979-8-89176-379-1
%F huang-etal-2025-multilingual-promise
%X Corporate ESG reports often contain statements that are vague or difficult to verify, creating room for potential greenwashing. Building automated systems to evaluate such claims is therefore a relevant research direction. Yet, existing analytical tools still show limited ability to verify sustainability promises in multiple languages, especially beyond English. This study examines how large language models (GPT-5) perform in verifying ESG-related promises across Chinese, Japanese, and English reports, aiming to provide a multilingual evaluation baseline. We assess four verification tasks using the PromiseEval datasets [1] in three languages, comparing five prompting strategies from zero-shot to five-shot learning, including Chain-of-Thought reasoning. The four subtasks are Promise Identification (PI), Evidence Status Assessment (ESA), Evidence Quality Evaluation (EQE), and Verification Timeline Prediction (VTP). The five-shot setting achieved the highest overall performance (71.12 % accuracy, 51.92 % Macro-F1). Although the accuracy results appear higher for Chinese (85.12 %) than for Japanese (68.94 %) and English (63.62 %), this mainly reflects class imbalance in the data. Hence, Macro-F1 provides a fairer comparison across languages. Among the four tasks, Evidence Quality Evaluation (EQE) remains the most difficult. While Chain-of-Thought prompting slightly lowers the overall average, it shows selective benefit on the more complex EQE task. Overall, this work offers a clearer multilingual baseline for ESG promise verification and supports the development of language-based tools that enhance the credibility and transparency of sustainability reporting.
%U https://aclanthology.org/2025.rocling-main.32/
%P 303-313
Markdown (Informal)
[Multilingual Promise Verification in ESG Reports with Large Language Model Performance Evaluation](https://aclanthology.org/2025.rocling-main.32/) (Huang et al., ROCLING 2025)
ACL