SOURCE-LINKED INTELLIGENCE

Representation of syntax in LLMs through the lens of linear distance and similarity-aware entropy

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Structural probes were introduced by Hewitt and Manning to reconstruct syntactic trees from a neural language model's latent representations. They are evaluated by calculating the proportion of syntactic tree edges correctly reconstructed over an annotated corpus (as measured by undirected unlabeled attachment score). Here, we disaggregate this measure, considering undirected attachment score by label (UASL), which assesses the reconstruction accuracy of each syntactic relation separately, establishing important differences among relations that overlap linguistic distinctions. Moreover, we ide

Read original source ↗ Open in workspace

recordType

paper

region

Global