Yucheng Du
yucheng-du
AI & ML interests
LLM reliability, mechanistic interpretability, AI auditing, computational linguistics
Recent Activity
updated a dataset 1 day ago
yucheng-du/recognition-refusal-misalignment published a dataset 1 day ago
yucheng-du/recognition-refusal-misalignment submitted a paper about 1 month ago
Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable QuestionsOrganizations
