Abstract: Large language models (LLMs), such as ChatGPT and Llama-2, have achieved state-of-the-art performance in many natural language processing (NLP) tasks. In this talk, I will discuss our recent investigation of their capabilities and limitations in several typical financial and legal tasks. For the financial applications, we explored areas such as the Chartered Financial Analyst (CFA) examination, sentiment analysis, and financial question answering, while in the legal domain, we focused on legal citation analysis. Through detailed experiments, we will demonstrate that, although current LLMs have achieved impressive performance, they still face significant limitations in these tasks.