Hannah Kim
About Hannah Kim
Hannah Kim is a research scientist focused on the sensitivity of large language models in multiple-choice questions and human-LLM collaborative annotation. She has co-authored a paper that characterizes large language models as rationalizers of knowledge-intensive tasks.
Work at Megagon Labs
Hannah Kim serves as a Research Scientist at Megagon Labs. In this role, she engages in advanced research focusing on large language models and their applications. Her work involves exploring the intricacies of how these models interact with human input and the implications for knowledge-intensive tasks.
Research Contributions
Hannah Kim has been involved in significant research studies, including one that examines the sensitivity of large language models to the order of options in multiple-choice questions. This research aims to understand how the arrangement of choices can influence model performance and decision-making.
Human-LLM Collaborative Annotation
Kim participated in research focused on human-LLM collaborative annotation. This study investigates the dynamics between human annotators and language models, aiming to enhance the efficiency and accuracy of data annotation processes in various applications.
Publications and Papers
Hannah Kim co-authored a paper that characterizes large language models as rationalizers of knowledge-intensive tasks. This publication contributes to the understanding of how these models process and rationalize information, providing insights into their capabilities and limitations.