HyperLens: Quantifying Cognitive Effort in LLMs with Fine-grained Confidence Trajectory

ArXi:2605.05741v1 Announce Type: new While Large Language Models (LLMs) achieve strong performance across diverse tasks, their inference dynamics remain poorly understood because of the limited resolution of existing analysis tools. In this work, we identify an intrinsic magnification mechanism in transformer architectures: deeper layers inherently magnify the small changes of layer-wise confidence, providing a fine-grained confidence trajectory. Building on this insight, we