pith. sign in

Are transformers universal approximators of sequence-to-sequence functions? International Conference on Learning Representations, 2020

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Provable Knowledge Acquisition and Extraction in One-Layer Transformers

cs.LG · 2025-07-28 · unverdicted · novelty 6.0

In a stylized one-layer transformer, pre-training encodes factual knowledge via relation-specific feature directions and attention patterns; fine-tuning extracts it through a relation-covering mechanism that succeeds when enough latent templates are triggered, with a failure regime explaining inauds

citing papers explorer

Showing 1 of 1 citing paper.

  • Provable Knowledge Acquisition and Extraction in One-Layer Transformers cs.LG · 2025-07-28 · unverdicted · none · ref 35

    In a stylized one-layer transformer, pre-training encodes factual knowledge via relation-specific feature directions and attention patterns; fine-tuning extracts it through a relation-covering mechanism that succeeds when enough latent templates are triggered, with a failure regime explaining inauds