LLM Reasoning and Architecture Language Understanding and Pragmatics

How do language models encode syntactic relations geometrically?

Do LLM embeddings use distance alone or also direction to represent syntax? Understanding whether neural networks can spontaneously develop symbolic-compatible geometric structures.

Note · 2026-02-23 · sourced from Cognitive Models Latent

The symbol-vector divide has been a core challenge in cognitive science since Smolensky (1987): syntactic trees are symbolic structures that seem incompatible with the vectorial representations of neural networks. The Structural Probe (Hewitt & Manning 2019) made partial progress — it showed that the existence of syntactic links between words is encoded in the distance between their corresponding embeddings. But whether the type and direction of syntactic relations were represented remained unknown.

The Polar Probe answers this: syntactic relations are coded by the relative direction between nearby embeddings, not just their distance. Using both distance and direction (a polar coordinate system), the Polar Probe recovers syntactic relation types and directions with nearly 2x the accuracy of the distance-only Structural Probe.

Three key findings:

  1. Complete syntactic encoding. The polar coordinate system captures existence, type, AND direction of syntactic relations — the full specification of a dependency tree is encoded in the geometry of LLM activations.

  2. Low-dimensional subspace. This encoding exists in a low-dimensional subspace of intermediate layers across many LLMs, and becomes increasingly precise in frontier models. This is not a brute-force representation but a compressed, structured one.

  3. Nested consistency. Similar syntactic relations are coded similarly across nested levels of syntactic trees. The encoding is not ad hoc for each syntactic instance but systematic — a genuine coordinate system.

The resolution of the symbol-vector divide is significant: LLMs don't need explicit symbolic mechanisms to represent symbolic structures. They spontaneously learn a geometry that explicitly represents the main symbolic structures of linguistic theory. This doesn't mean LLMs "understand" syntax in a human sense, but it demonstrates that connectionist architectures can natively develop symbolic-compatible representations — the two paradigms are not incompatible.

This connects to Do transformer static embeddings actually encode semantic meaning? at a different structural level: static embeddings encode semantic features, while intermediate activations encode syntactic relations. Together they suggest LLM representations are far richer and more structured than the "statistical patterns" dismissal implies.


Source: Cognitive Models Latent

Related concepts in this collection

Concept map
13 direct connections · 104 in 2-hop network ·medium cluster

Click a node to walk · click center to open · click Open full network for a force-directed map

your link semantically near linked from elsewhere
Original note title

a polar coordinate system in llm activations encodes both type and direction of syntactic relations — resolving the symbol-vector divide