Showing 2026Show all
2 papers · 1 filter
cs.LG2026
BaRA: Bayesian Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning
Zhibin Duan, Yuhong Wang, Jiahong Fu +3
While Low-rank adaptation (LoRA) enables highly efficient fine-tuning by constraining task-specific updates to fixed low-rank subspaces, this rigid design limits representational f…
cs.LG2026
Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling
Zhibin Duan, Guowei Rong, Zhuo Li +3
Reward models learned from human preferences are central to aligning large language models (LLMs) via reinforcement learning from human feedback, yet they are often vulnerable to r…