Thu Jul 2 · 11:10 AM · R1 (Auditorium Meeting 1) Learning from Giants: Distilling Attribute-Aligned LLM Evaluators for Educational Essay Assessment in LLMs for Writing Assessment, Feedback, and Fairness
Thu Jul 2 · 4:30 PM · North 210 Decoding Latent Reasoning: Mechanistic Interpretability of Chain of Continuous Thought with Sparse Autoencoders in Modeling, Measuring, and Interpreting Thinking Processes with AI