CSE - Making Better Large Language Models

Large language models (LLMs) are being used in many places. Our lab is looking for self-motivated undergraduate students that are interested in developing better LLMs or finding better methods to use LLMs. We study LLMs in various real-world scenarios from open-domain question answering to emotional support, material discovery, and education for deaf and hard of hearing students. We aim to improve several types of abilities of LLMs: (a) follow complex instructions, (b) perform complex reasoning, (c) detect and reduce hallucination, (d) provide personalized responses, (e) simulate behaviors of specific population, (f) forget private or sensitive information, and (g) understand tables and charts in scientific literature.