2 papers
cs.AI2026
Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability
Xinyan Jiang, Ninghao Liu, Di Wang +1
Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning. We introduce TRACED, a framework that assesses reasoning quality th…
cs.LG2025
EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification
Lin Zhang, Wenshuo Dong, Zhuoran Zhang +5
Understanding the internal mechanisms of transformer-based language models remains challenging. Mechanistic interpretability based on circuit discovery aims to reverse engineer neu…