15 citations · 15 across the 5 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Erased, Rerouted, or Rescaled? Post-Training and the Causal Quotient of a Language Model's Belief State
Weihan Li, Tianshi Zheng, Junhao Wu +1
What happens to information a pretrained model already encodes when post-training no longer rewards using it? The common language of representation compression conflates three fate…
cs.LG2026
Memorize Theorems, Not Instances: Probing SFT Generalization through Mathematical Reasoning
Ruiying Peng, Mengyu Yang, Jing Lei +3
Supervised Fine-Tuning (SFT) is widely used for task-specific adaptation, yet recent work shows it systematically undermines reasoning generalization. We argue the root cause is no…