Seonglae Cho

1. CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features
   2025/08/18 by Seonglae Cho, Zekun Wu, Cho, Seonglae +3 · 1 citation
   Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification
2. Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects
   2026/07/22 by Seonglae Cho, Zekun Wu, Kleyton Da Costa +3
   #cs.LG #cs.CL
3. OptimismBench: Forecasting Bias and the Alignment Effect in Language Model Judgment
   2026/07/29 by Seonglae Cho, Adriano Koshiyama
   Computer Science · #cs.CL