@inproceedings{hasan-etal-2024-llm,
    title = "{LLM}-{GE}m: Large Language Model-Guided Prediction of People{'}s Empathy Levels towards Newspaper Article",
    author = "Hasan, Md Rakibul  and
      Hossain, Md Zakir  and
      Gedeon, Tom  and
      Rahman, Shafin",
    editor = "Graham, Yvette  and
      Purver, Matthew",
    booktitle = "Findings of the Association for Computational Linguistics: EACL 2024",
    month = mar,
    year = "2024",
    address = "St. Julian{'}s, Malta",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/declare-journal/2024.findings-eacl.147/",
    doi = "10.18653/v1/2024.findings-eacl.147",
    pages = "2215--2231",
    abstract = "Empathy {--} encompassing the understanding and supporting others' emotions and perspectives {--} strengthens various social interactions, including written communication in healthcare, education and journalism. Detecting empathy using AI models by relying on self-assessed ground truth through crowdsourcing is challenging due to the inherent noise in such annotations. To this end, we propose a novel system, named Large Language Model-Guided Empathy \textit{(LLM-GEm)} prediction system. It rectifies annotation errors based on our defined annotation selection threshold and makes the annotations reliable for conventional empathy prediction models, e.g., BERT-based pre-trained language models (PLMs). Previously, demographic information was often integrated numerically into empathy detection models. In contrast, our \textit{LLM-GEm} leverages GPT-3.5 LLM to convert numerical data into semantically meaningful textual sequences, enabling seamless integration into PLMs. We experiment with three \textit{NewsEmpathy} datasets involving people{'}s empathy levels towards newspaper articles and achieve state-of-the-art test performance using a RoBERTa-based PLM. Code and evaluations are publicly available at \url{https://github.com/hasan-rakibul/LLM-GEm}."
}