@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://preview.aclanthology.org/Author-page-Marten-During-lu/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 {\textquotedblleft}Opportunity{\textquotedblright} or {\textquotedblleft}Risk{\textquotedblright} 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."
}