@inproceedings{mishra-2023-esg,
title = "{ESG} Impact Type Classification: Leveraging Strategic Prompt Engineering and {LLM} Fine-Tuning",
author = "Mishra, Soumya",
editor = "Chen, Chung-Chi and
Huang, Hen-Hsen and
Takamura, Hiroya and
Chen, Hsin-Hsi and
Sakaji, Hiroki and
Izumi, Kiyoshi",
booktitle = "Proceedings of the Sixth Workshop on Financial Technology and Natural Language Processing",
month = nov,
year = "2023",
address = "Bali, Indonesia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.finnlp-2.11",
doi = "10.18653/v1/2023.finnlp-2.11",
pages = "72--78",
abstract = "In this paper, we describe our approach to the ML-ESG-2 shared task, co-located with the FinNLP workshop at IJCNLP-AACL-2023. The task aims at classifying news articles into categories reflecting either {``}Opportunity{''} or {``}Risk{''} from an ESG standpoint for companies. Our innovative methodology leverages two distinct systems for optimal text classification. In the initial phase, we engage in prompt engineering, working in conjunction with semantic similarity and using the Claude 2 LLM. Subsequently, we apply fine-tuning techniques to the Llama 2 and Dolly LLMs to enhance their performance. We report the results of five different approaches in this paper, with our top models ranking first in the French category and sixth in the English category.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mishra-2023-esg">
<titleInfo>
<title>ESG Impact Type Classification: Leveraging Strategic Prompt Engineering and LLM Fine-Tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Soumya</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Financial Technology and Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hen-Hsen</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Sakaji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiyoshi</namePart>
<namePart type="family">Izumi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bali, Indonesia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe our approach to the ML-ESG-2 shared task, co-located with the FinNLP workshop at IJCNLP-AACL-2023. The task aims at classifying news articles into categories reflecting either “Opportunity” or “Risk” from an ESG standpoint for companies. Our innovative methodology leverages two distinct systems for optimal text classification. In the initial phase, we engage in prompt engineering, working in conjunction with semantic similarity and using the Claude 2 LLM. Subsequently, we apply fine-tuning techniques to the Llama 2 and Dolly LLMs to enhance their performance. We report the results of five different approaches in this paper, with our top models ranking first in the French category and sixth in the English category.</abstract>
<identifier type="citekey">mishra-2023-esg</identifier>
<identifier type="doi">10.18653/v1/2023.finnlp-2.11</identifier>
<location>
<url>https://aclanthology.org/2023.finnlp-2.11</url>
</location>
<part>
<date>2023-11</date>
<extent unit="page">
<start>72</start>
<end>78</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ESG Impact Type Classification: Leveraging Strategic Prompt Engineering and LLM Fine-Tuning
%A Mishra, Soumya
%Y Chen, Chung-Chi
%Y Huang, Hen-Hsen
%Y Takamura, Hiroya
%Y Chen, Hsin-Hsi
%Y Sakaji, Hiroki
%Y Izumi, Kiyoshi
%S Proceedings of the Sixth Workshop on Financial Technology and Natural Language Processing
%D 2023
%8 November
%I Association for Computational Linguistics
%C Bali, Indonesia
%F mishra-2023-esg
%X In this paper, we describe our approach to the ML-ESG-2 shared task, co-located with the FinNLP workshop at IJCNLP-AACL-2023. The task aims at classifying news articles into categories reflecting either “Opportunity” or “Risk” from an ESG standpoint for companies. Our innovative methodology leverages two distinct systems for optimal text classification. In the initial phase, we engage in prompt engineering, working in conjunction with semantic similarity and using the Claude 2 LLM. Subsequently, we apply fine-tuning techniques to the Llama 2 and Dolly LLMs to enhance their performance. We report the results of five different approaches in this paper, with our top models ranking first in the French category and sixth in the English category.
%R 10.18653/v1/2023.finnlp-2.11
%U https://aclanthology.org/2023.finnlp-2.11
%U https://doi.org/10.18653/v1/2023.finnlp-2.11
%P 72-78
Markdown (Informal)
[ESG Impact Type Classification: Leveraging Strategic Prompt Engineering and LLM Fine-Tuning](https://aclanthology.org/2023.finnlp-2.11) (Mishra, FinNLP-WS 2023)
ACL