Cite
Notes
Only stored in your browser.
Attribution
Improving LLM Safety Alignment with Dual-Objective Optimization
arXiv 2025
Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
arXiv 2024
Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining
arXiv 2023
from 3 papers
Song Mei
Chongyu Fan
David Huang
Dawn Song
professor
Jiancheng Liu
Jinghan Jia
Ruiqi Zhang
Sijia Liu
Tianneng Shi
Will Cai