2 papers
cs.LG2026
Safe Inference-Time Alignment via Lagrangian Reward Augmentation
Yaswanth Chittepu, Ativ Joshi, Sohini Chintala +1
Inference-time alignment steers a frozen language model during decoding using auxiliary reward signals, avoiding the cost of repeated weight updates. However, existing inference-ti…
cs.LG2026
Safe RLHF Beyond Expectation: Stochastic Dominance for Universal Spectral Risk Control
Yaswanth Chittepu, Ativ Joshi, Rajarshi Bhattacharjee +1
Safe Reinforcement Learning from Human Feedback (RLHF) typically enforces safety through expected cost constraints, but the expectation captures only a single statistic of the cost…