To develop techniques using state-of-the-art AI methods to enrich the experience around LLM usage.
Skills Required: Python, ML, DL, LLMs, Hugging Face, exposure to UI development
Experiment with Java Mircroservice and create reusable flows using Watson X prompt engineering
The main idea of this work is to explore regions where a given model does not work. Using this information, can we extract relevant feedback data that can be used to improve model's performance?
The work would be around exploring the following:
explore state-of-the-art NLP models such as BERT to fine-tune to infuse numeric semantics and use it to learn KGEs.
Define novel scoring function to enhance predictions for Numerical Quantities which is not been explored in the literature.
Hands-on experiments to explore limitations of current Knowledge Graph based QA methods and benchmark them.