Financial Named Entity Recognition: How Far Can LLM Go?
This work addresses the effectiveness of generic LLMs for financial NER, a foundational task in intelligent financial analytics, by providing a systematic evaluation that is incremental in nature.
The paper systematically evaluates state-of-the-art large language models and prompting methods for financial named entity recognition, highlighting their strengths, limitations, and five failure types to provide insights into their potential and challenges in domain-specific tasks.
The surge of large language models (LLMs) has revolutionized the extraction and analysis of crucial information from a growing volume of financial statements, announcements, and business news. Recognition for named entities to construct structured data poses a significant challenge in analyzing financial documents and is a foundational task for intelligent financial analytics. However, how effective are these generic LLMs and their performance under various prompts are yet need a better understanding. To fill in the blank, we present a systematic evaluation of state-of-the-art LLMs and prompting methods in the financial Named Entity Recognition (NER) problem. Specifically, our experimental results highlight their strengths and limitations, identify five representative failure types, and provide insights into their potential and challenges for domain-specific tasks.