Yuanshun Yao

Researcher at ByteDance Research working on large language model trustworthiness, alignment evaluation, and the development of frameworks for systematic assessment of LLM safety and reliability.

Sources in this wiki

• Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models' Alignment

Topics

• LLM Safety and Adversarial Robustness, LLM Alignment