SOURCE-LINKED INTELLIGENCE

Encoded but Not Decoded: Layer-Localized Evidence for a Three-Level Gap in LLM Syntax

arXiv · AI, language, vision and robotics · article · Sep 24, 2026 · UTC

A language model can fail a syntactic test in two distinct ways: by not encoding the relevant structure, or by encoding it but failing to use it at the output. Behavioral evaluation alone cannot tell these apart. We propose a three-level evaluation framework (behavioral deployment, LM-head readout, and probe recoverability) measured on the same items under the same binary decision. Using a compact trilingual (English, Chinese, German) control-dependency benchmark, we find that probe recoverability exceeds or equals LM-head readout, which in turn exceeds or equals behavioral deployment, across

Read original source ↗ Open in workspace

recordType

paper

region

Global