@inproceedings{lee-kim-2026-esgpt,
title = "{ESGPT}: A Data-Centric {ESG} Language Model with Unified Instruction and Benchmark Resources",
author = "Lee, Jaeyoung and
Kim, Misuk",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Junyi Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1361/",
doi = "10.18653/2026.emnlp-main.1361",
pages = "31043--31064",
ISBN = "979-8-89176-459-0",
abstract = "ESG analysis requires complex language understanding across diverse sources, including corporate reports, news, and disclosures, for tasks such as ESG relevance detection, action interpretation, impact analysis, and question answering. However, existing ESG datasets are fragmented by task and source, with heterogeneous formats and annotation schemes, limiting their use for training general-purpose ESG LLMs and unified evaluation. In this work, we construct ESG-Instruct, a 30,000-instance ESG instruction dataset built from public ESG resources, and ESGU-Bench, an ESG understanding benchmark covering six representative ESG tasks. Based on these resources, we further develop ESGPT, an 8B ESG-specialized LLM, and evaluate it against diverse open-source and API-based LLMs. Experimental results show that general-purpose LLMs exhibit substantial performance variation across ESG tasks, while ESGPT, despite its relatively small scale, achieves the best performance on multiple ESG tasks. This work provides unified data and benchmark resources for training and evaluating ESG-specialized LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-kim-2026-esgpt">
<titleInfo>
<title>ESGPT: A Data-Centric ESG Language Model with Unified Instruction and Benchmark Resources</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jaeyoung</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Misuk</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>ESG analysis requires complex language understanding across diverse sources, including corporate reports, news, and disclosures, for tasks such as ESG relevance detection, action interpretation, impact analysis, and question answering. However, existing ESG datasets are fragmented by task and source, with heterogeneous formats and annotation schemes, limiting their use for training general-purpose ESG LLMs and unified evaluation. In this work, we construct ESG-Instruct, a 30,000-instance ESG instruction dataset built from public ESG resources, and ESGU-Bench, an ESG understanding benchmark covering six representative ESG tasks. Based on these resources, we further develop ESGPT, an 8B ESG-specialized LLM, and evaluate it against diverse open-source and API-based LLMs. Experimental results show that general-purpose LLMs exhibit substantial performance variation across ESG tasks, while ESGPT, despite its relatively small scale, achieves the best performance on multiple ESG tasks. This work provides unified data and benchmark resources for training and evaluating ESG-specialized LLMs.</abstract>
<identifier type="citekey">lee-kim-2026-esgpt</identifier>
<identifier type="doi">10.18653/2026.emnlp-main.1361</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1361/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>31043</start>
<end>31064</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ESGPT: A Data-Centric ESG Language Model with Unified Instruction and Benchmark Resources
%A Lee, Jaeyoung
%A Kim, Misuk
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Junyi Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F lee-kim-2026-esgpt
%X ESG analysis requires complex language understanding across diverse sources, including corporate reports, news, and disclosures, for tasks such as ESG relevance detection, action interpretation, impact analysis, and question answering. However, existing ESG datasets are fragmented by task and source, with heterogeneous formats and annotation schemes, limiting their use for training general-purpose ESG LLMs and unified evaluation. In this work, we construct ESG-Instruct, a 30,000-instance ESG instruction dataset built from public ESG resources, and ESGU-Bench, an ESG understanding benchmark covering six representative ESG tasks. Based on these resources, we further develop ESGPT, an 8B ESG-specialized LLM, and evaluate it against diverse open-source and API-based LLMs. Experimental results show that general-purpose LLMs exhibit substantial performance variation across ESG tasks, while ESGPT, despite its relatively small scale, achieves the best performance on multiple ESG tasks. This work provides unified data and benchmark resources for training and evaluating ESG-specialized LLMs.
%R 10.18653/2026.emnlp-main.1361
%U https://aclanthology.org/2026.emnlp-main.1361/
%U https://doi.org/10.18653/2026.emnlp-main.1361
%P 31043-31064
Markdown (Informal)
[ESGPT: A Data-Centric ESG Language Model with Unified Instruction and Benchmark Resources](https://aclanthology.org/2026.emnlp-main.1361/) (Lee & Kim, EMNLP 2026)
ACL