3 papers
cs.LG2026
Risk-Conditioned Fine-Tuning of Large Language Models
Zixuan Liu, Fangzheng Wu, Brian Summa +2
Large Language Models (LLMs) are increasingly deployed in settings where rare but severe harmful generations can have significant consequences. Existing Risk-Averse RLHF addresses…
cs.LG2026
Adaptive Multilevel Twisted Sequential Monte Carlo for Rare Events Estimation in Language Models
Zixuan Liu, Fangzheng Wu, Brian Summa +1
Rare unsafe behaviors in large language models can remain practically significant even when their probability is extremely small, particularly at deployment scales involving millio…
cs.LG2026
Robust General Utility for Reinforcement Learning
Zixuan Liu, Fangzheng Wu, Brian Summa +1
Reinforcement learning (RL) with general utility extends classic RL by optimizing an arbitrary utility functional of the policy-induced occupancy measure, thereby enabling a broade…