Taiwei Shi

Projects

Things I do, including research, academic course projects, and miscellaneous interests.

Research

Research publications for fans of natural language processing, computational social science, and machine learning.

How Susceptible are Large Language Models to Ideological Manipulation?
ICLR SeT LLM Workshop, 2024
Can Language Model Moderators Improve the Health of Online Discourse?
NAACL, 2024
Safer-Instruct Aligning Language Models with Automated Preference Data
NAACL, 2024
Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation
EMNLP, 2023
Combining symbolic and neural story generation
AAAI Creative AI Workshop, 2023
Investigating AAVE in Question Answering Systems
GT Thesis, 2023