Role

• Developed an end-to-end financial question answering system using Large Language Models (LLMs) on FinQA dataset
• Designed a negative sampling method based on clustering, improving the RoBerta-Large based Retrieval model’s R@3 metric by 2.4% on test set.
• Implemented Chain of Thought (COT), self consistency and self prompting methods for with GPT-3.5, GPT-4-turbo and PaLM2 Large Language Models. <!– Heading 1 ======

Heading 2

Heading 3 ====== –>