arxiv:2601.12294
Dawei Li
wjldw
AI & ML interests
LLM, NLP, Data Mining
Recent Activity
upvoted a paper 10 days ago
RubricBench: Aligning Model-Generated Rubrics with Human Standards upvoted a paper about 1 month ago
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration upvoted a paper about 2 months ago
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models