Vinay Samuel

Vinay Samuel

Statistics and Machine Learning student at Carnegie Mellon Univeristy

About Me

I am a senior at Carnegie Mellon University, with a passion for Natural Language Processing (NLP) and Artificial Intelligence (AI). In my undergraduate years I have been fortunate to work with several distinguished advisors on cutting-edge projects.

Under the guidance of Prof. Karthik Narasimhan in the Princeton NLP Group, I led research on developing PersonaGym, the first evaluation framework for persona agents in Large Language Models (LLMs). This project has contributed significantly to our understanding of the abilty of LLMs to take on personas as they interact in various environments as agents.

I collaborated with Prof. Cornelia Caragea on ImplicitAVE was the first open-sourced dataset for implicit attribution value extraction. Our work was accepted to ACL Findings 2024, marking a significant advancement in the field of attribute value extraction.

Currently, I’m working with Prof. Daphne Ippolito on LLM output control, exploring ways to enhance the reliability and consistency of AI-generated content. I am concurrently working with Yijia Zhou and Prof. Diyi Yang on a project aimed at Human-AI collaboration between users and Language Model agents on multiple tasks. Stay tuned for more details as we release our work!

These diverse experiences have solidified my commitment to pushing the boundaries of NLP and AI, and I’m excited to continue this journey in my graduate studies and beyond.

News