Zifan Carl Guo

MIT EECS

MIT CSAIL

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Interpretability & Mechanistic Interp (1)Reasoning & Chain-of-Thought (1)

Frequent co-authors

Laura Ruis (1)Jacob Andreas (1)Belinda Z. Li (1)

Papers (1)

Jun 30, 2026

MIT CSAIL1w ago

Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision

Fixed counterfactual explanations can lead LMs to generate more accurate introspections about their behaviors, even as those behaviors change over time.

Zifan Carl Guo, Laura Ruis, Jacob Andreas +1

Interpretability & Mechanistic Interp Reasoning & Chain-of-Thought

Search

Zifan Carl Guo

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)