3 papers
cs.CL2025
Steering Information Utility in Key-Value Memory for Language Model Post-Training
Chunyuan Deng, Ruidi Chang, Hanjie Chen
Recent advancements in language models (LMs) have marked a shift toward the growing importance of post-training. Yet, post-training approaches such as supervised fine-tuning (SFT)…
cs.CL2025
Learning Distribution-Wise Control in Representation Space for Language Models
Chunyuan Deng, Ruidi Chang, Hanjie Chen
Interventions in language models (LMs) are applied strategically to steer model behavior during the forward pass. Learnable interventions, also known as representation fine-tuning,…
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…