task-specificity-emerges-from-readout

OUT derived (depth 2)

Created 2026-08-25T03:05:14+00:00 · Reviewed 2026-08-25T04:28:09+00:00

Task-specificity in embedding quality is a readout phenomenon: the internal feature geometry is largely model-independent (convergent across architectures), while MTEB's no-dominant-model result arises because each task's unembedding/projection head selects a different subspace of the same shared geometric structure.

Justifications

SL — Cross-model geometric convergence (Park validated on Gemma+LLaMA, SAE universal) combined with MTEB's irreducible task variance localises the source of specificity to the readout layer rather than the internal representation.

Antecedents (all must be IN):

  • OUT task-specificity-vs-feature-universality — Embedding model quality is irreducibly task-specific (no single model dominates MTEB's 8 tasks) while internal feature representations are largely model-independent (SAE features transfer across architectures), separating output-space competition from internal geometric convergence.
  • IN multi-model-geometric-convergence — Both the polytope/orthogonality geometry (Park, validated on Gemma-2B and LLaMA-3-8B) and sparse feature structure (SAE, universal across architectures) converge on the finding that transformer representation spaces carry model-independent geometric invariants.

Dependents

These beliefs depend on this one: