3 papers
cs.LG2026
Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework
Jiaqi Weng, Han Zheng, Hanyu Zhang +6
Sparse autoencoders (SAEs) enable interpretability research by decomposing entangled model activations into monosemantic features. However, under what circumstances SAEs derive mos…
cs.CL2025
Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models
Chengao Li, Hanyu Zhang, Yunkun Xu +3
Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful technique for aligning large language models (LLMs) with human preferences. However, effectively alignin…
cs.CL2025
Controlling Large Language Models Through Concept Activation Vectors
Hanyu Zhang, Xiting Wang, Chengao Li +2
As large language models (LLMs) are widely deployed across various domains, the ability to control their generated outputs has become more critical. This control involves aligning…