4 papers
Chronos: Learning Temporal Dynamics of Reasoning Chains for Test-Time Scaling
Kai Zhang, Jiayi Liao, Chengpeng Li +3
Test-Time Scaling (TTS) has emerged as an effective paradigm for improving the reasoning performance of large language models (LLMs). However, existing methods -- most notably majo…
Differentially Private Subspace Fine-Tuning for Large Language Models
Lele Zheng, Xiang Wang, Tao Zhang +3
Fine-tuning large language models on downstream tasks is crucial for realizing their cross-domain potential but often relies on sensitive data, raising privacy concerns. Differenti…
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…
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…