In recent years, computer science researchers have introduced large language models (LLM), which are deep-learning based NLP algorithms, such as Google's BERT, that consider word contexts, e.g., other words in the same text, and word sequences in summarizing texts. These researchers show that LLM can significantly outperform simpler NLP models that assume a bag-of-words structure in tasks such as sentiment classification in general texts, language translation, and question answering. In this project, we will label the sentiments of a dataset of financial texts that mention multiple entities (companies) and use the dataset to train and fine-tune several NLP algorithms including LLM. One example of such LLM is FinBERT (https://finbert.ai/), a pre-trained deep learning NLP algorithm specific to finance domain.