4 papers · 1 filter
Less Sycophancy, Stronger Refusal? Lessons for AI Safety from Mechanistic Interpretability
Xu Wang, Difan Zou, Xuansheng Wu
Reliable refusal of harmful requests is essential to the safe deployment of language models. Because excessive eagerness to please users may undermine existing refusal capabilities…
Beyond Token Scale: Chunk-Level Sparse Autoencoders for Reliable Semantic Feature Discovery
Xu Wang, Yifan Yang, TingHao YU +1
Sparse autoencoders (SAEs) expose features that help us understand and steer language models, but faithful reconstruction does not guarantee informative concepts. Token-level objec…
Model Unlearning via Sparse Autoencoder Subspace Guided Projections
Xu Wang, Zihao Li, Benyou Wang +2
Large language models (LLMs) store vast amounts of information, making them powerful yet raising privacy and safety concerns when selective knowledge removal is required. Existing…
Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
Xu Wang, Yan Hu, Wenyu Du +3
Fine-tuning significantly improves the performance of Large Language Models (LLMs), yet its underlying mechanisms remain poorly understood. This paper aims to provide an in-depth i…