This paper explores the emerging field of context-aware financial advisory systems, focusing on integrating sentiment analysis and personalized investment strategies. Leveraging advancements in large language models (LLMs) applied to finance, we investigate how these systems provide nuanced financial advice by considering market sentiment, individual investor profiles, and real-time economic contexts. Our research reviews insights from studies published between 2020 and 2024, examining finance-specific LLMs and natural language processing techniques. Key challenges such as data privacy, regulatory compliance, and future research directions are discussed. While existing technologies like robo-advisors have automated investment advice, they often lack the contextual adaptability needed in today’s markets. Our survey addresses this by examining how LLMs, sentiment analysis, and personalization can create more responsive advisory systems. These technologies can interpret complex market signals and unstructured data to generate personalized advice that adapts to evolving conditions. By identifying key challenges and recent advancements, our study offers a roadmap for developing next-gen financial advisory systems capable of navigating modern financial complexities with personalized guidance.