4 papers · 1 filter
Steering Vectors for Competing Ethical Frameworks Are Interchangeable: A Competing-Target Test for Activation Steering
Weilun Xu, Zipeng Sun
Activation steering adds a vector to a model's hidden states to control a named behaviour. A gain on that behaviour, however, does not show that the vector controls it directly: it…
FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space
Jiahong Liu, Ram Samarth B B, Xinyu Fu +4
Federated learning enables privacy-preserving collaborative training, but highly heterogeneous client data remain challenging, especially in graph federated learning where clients…
Revisiting Degree-Corrected Spectral Clustering: a Condition-Free Spectral Analysis and Extension
Wei Li, Xiaojian Li, Meng Qin +4
Spectral clustering is a representative graph clustering technique with strong interpretability and theoretical guarantees. Degree-corrected spectral clustering (DCSC) has emerged…
On the Non-decoupling of Supervised Fine-tuning and Reinforcement Learning in Post-training
Xueyan Niu, Bo Bai, Wei Han +1
Post-training of large language models routinely interleaves supervised fine-tuning (SFT) with reinforcement learning (RL). These two methods have different objectives: SFT minimiz…