3 papers
cs.LG2025
Interpretable Reward Model via Sparse Autoencoder
Shuyi Zhang, Wei Shi, Sihang Li +3
Large language models (LLMs) have been widely deployed across numerous fields. Reinforcement Learning from Human Feedback (RLHF) leverages reward models (RMs) as proxies for human…
cs.CL2025
SAFER: Probing Safety in Reward Models with Sparse Autoencoder
Wei Shi, Ziyuan Xie, Sihang Li +1
Reinforcement learning from human feedback (RLHF) is a key paradigm for aligning large language models (LLMs) with human values, yet the reward models at its core remain largely op…
cs.LG2025
Route Sparse Autoencoder to Interpret Large Language Models
Wei Shi, Sihang Li, Tao Liang +4
Mechanistic interpretability of large language models (LLMs) aims to uncover the internal processes of information propagation and reasoning. Sparse autoencoders (SAEs) have demons…