← Back to all news
arXiv Machine Learning By Aryan Sharma, Cutter Dawes, Shivam Raval

Dissociating Decodability and Causal Use in Bracket-Sequence Transformers

Read the original on arXiv Machine Learning →

arXiv:2604. 22128v2 Announce Type: replace-cross Abstract: When trained on tasks requiring an understanding of hierarchical structure, transformers have been found to represent this hierarchy in distinct ways: in the geometry of the residual stream, and in stack-like attention patterns maintaining a last-in, first-out ordering.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 25

Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs

The paper demonstrates that Large Language Models, despite their non‑linear components, exhibit a fundamental linearity property: when inputs from two distinct text streams are linearly combined, the model outputs a superposition of the individual next‑token distributions. This "Superposition Linearity Hypothesis" appears to be an intrinsic feature of the Transformer architecture, tends to weaken during pretraining, but can be largely restored with lightweight fine‑tuning. The authors also present a guided decoding method that separates the superposed outputs, allowing two coherent continuations to be generated from a single forward pass.

By Pavel Tikhonov, Anton Korznikov, Matvey Mikhalchuk, Nikita Dragunov, Temurbek Rahmatullaev, Polina Druzhinina, Anton Razzhigaev, Ivan Oseledets, Elena Tutubalina
llmsfine-tuning
More like this →
arXiv Machine Learning
Jun 17

An expressivity analysis of hierarchical modelling in deep transformers via bounded-depth grammars

arXiv:2606. 17522v1 Announce Type: cross Abstract: Deep neural networks are widely believed to derive their expressive power from their ability to form \textbf{hierarchical representations}, capturing progressively more abstract and compositional features across layers.

By Vinoth Nandakumar, Qiang Qu, Pramod Thebe, Sakshi Khachariya, Tongliang Liu
llms
More like this →