Scholarlink

This systematic literature review examines how Large Language Models (LLMs) have transformed financial statement analysis by integrating narrative (textual) and quantitative data. Focusing on publications from 2017 to the present, we identified peer-reviewed articles, working papers, and conference proceedings from leading databases (Scopus, Web of Science, SSRN, and Google Scholar). Our review highlights four principal areas where LLMs have shown particular promise: risk and fraud detection, narrative summarization and sentiment analysis, Environmental, Social, and Governance (ESG) and sustainability reporting, and the integration of textual disclosures with traditional accounting metrics. These models – ranging from general-purpose Transformers (e.g., GPT, BERT) to specialized financial variants (e.g., FinBERT) – often outperform earlier machine learning approaches in tasks requiring nuanced linguistic understanding, but face challenges such as domain adaptation, interpretability, and potential model biases. Synthesizing existing studies, we observe a growing trend toward domain-specific LLMs that process both unstructured narrative text (e.g., annual reports, footnotes) and structured financial data, providing richer insights for auditors, analysts, and investors. However, empirical findings highlight concerns about data availability, reproducibility, and regulatory compliance. We suggest future research on standardized financial corpora for training robust LLMs, improved explainability tools for high-stakes decisions, and ethical frameworks to mitigate algorithmic bias. This review underscores LLMs’ transformative potential in economic and accounting domains while cautioning against uncritical deployment in sensitive settings.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Applications of Large Language Models in the Innovative Analysis of Economic and Accounting Documentation: A Systematic Review of Recent Advances and Practical Implications

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Daria Trachova,
  • Viacheslav Trachov,
  • Olena Demchuk,
  • Andrii Karpenko,
  • Ilona Prykhodko

摘要

This systematic literature review examines how Large Language Models (LLMs) have transformed financial statement analysis by integrating narrative (textual) and quantitative data. Focusing on publications from 2017 to the present, we identified peer-reviewed articles, working papers, and conference proceedings from leading databases (Scopus, Web of Science, SSRN, and Google Scholar). Our review highlights four principal areas where LLMs have shown particular promise: risk and fraud detection, narrative summarization and sentiment analysis, Environmental, Social, and Governance (ESG) and sustainability reporting, and the integration of textual disclosures with traditional accounting metrics. These models – ranging from general-purpose Transformers (e.g., GPT, BERT) to specialized financial variants (e.g., FinBERT) – often outperform earlier machine learning approaches in tasks requiring nuanced linguistic understanding, but face challenges such as domain adaptation, interpretability, and potential model biases. Synthesizing existing studies, we observe a growing trend toward domain-specific LLMs that process both unstructured narrative text (e.g., annual reports, footnotes) and structured financial data, providing richer insights for auditors, analysts, and investors. However, empirical findings highlight concerns about data availability, reproducibility, and regulatory compliance. We suggest future research on standardized financial corpora for training robust LLMs, improved explainability tools for high-stakes decisions, and ethical frameworks to mitigate algorithmic bias. This review underscores LLMs’ transformative potential in economic and accounting domains while cautioning against uncritical deployment in sensitive settings.