3 papers
cs.LG2026
UMM-RM: An Upcycle-and-Merge MoE Reward Model for Mitigating Reward Hacking
Lingling Fu, Yongfu Xue
Reward models (RMs) are a critical component of reinforcement learning from human feedback (RLHF). However, conventional dense RMs are susceptible to exploitation by policy models…
cs.CL2026
PIRA: Preference-Oriented Instruction-Tuned Reward Models with Dual Aggregation
Yongfu Xue
Reward models are pivotal for aligning Large Language Models (LLMs) with human preferences. Existing approaches face two key limitations: Discriminative reward models require large…
cs.LG2026
Optimizing Fine-Tuning through Advanced Initialization Strategies for Low-Rank Adaptation
Yongfu Xue
The rapid development of parameter-efficient fine-tuning methods has noticeably improved the efficiency of adapting large language models. Among these, LoRA has gained widespread p…