Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Spherical Steering: Geometry-Aware Activation Rotation for Language Models
Zejia You, Chunyuan Deng, Hanjie Chen
Inference-time steering offers a promising way to control language models (LMs) without retraining. However, standard approaches typically rely on activation addition, which inevit…
cs.LG2025
SAFR: Neuron Redistribution for Interpretability
Ruidi Chang, Chunyuan Deng, Hanjie Chen
Superposition refers to encoding representations of multiple features within a single neuron, which is common in deep neural networks. This property allows neurons to combine and r…
cs.LG2024
Language Models are Symbolic Learners in Arithmetic
Chunyuan Deng, Zhiqi Li, Roy Xie +2
The prevailing question in LM performing arithmetic is whether these models learn to truly compute or if they simply master superficial pattern matching. In this paper, we argues f…