@inproceedings{nishida-utsuro-2025-generating,
    title = "Generating Financial News Articles from Factors of Stock Price Rise / Decline by {LLM}s",
    author = "Nishida, Shunsuke  and
      Utsuro, Takehito",
    editor = "Chen, Chung-Chi  and
      Moreno-Sandoval, Antonio  and
      Huang, Jimin  and
      Xie, Qianqian  and
      Ananiadou, Sophia  and
      Chen, Hsin-Hsi",
    booktitle = "Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal)",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.finnlp-1.18/",
    pages = "184--195",
    abstract = "In this paper, we study the task of generating financial news articles related to stock price fluctuations. Traditionally, reporters manually write these articles by identifying the causes behind significant stock price volatility. However, this process is time-consuming, limiting the number of articles produced. To address this, the study explores the use of generative AI to automatically generate such articles. The AI system, similar to human reporters, would analyze stock price volatility and determine the underlying factors contributing to these fluctuations. To support this approach, we introduces a Japanese dataset called JFinSR, which includes stock price fluctuation rankings from ``Kabutan'' and related financial information regarding factors of stock price rise / decline from ``Nihon Keizai Shimbun (Nikkei).'' Using this dataset, we implement the few-shot learning technique on large language models (LLMs) to enable automatic generation of high-quality articles from factors of stock price rise / decline that are available in Nikkei. In the evaluation, we compare zero-shot and few-shot learning approaches, where the few-shot learning achieved the higher F1 scores in terms of ROUGE-1/ROUGE-L metrics."
}