Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs
Transformers superpose next-token distributions from mixed text streams, and fine-tuning can restore that linearity.
The paper argues that Transformers exhibit linear superposition: when inputs from distinct text streams are linearly combined, the model outputs a superposition of the individual next-token distributions. The authors treat this as an architectural property rather than a consequence of training, and report that it tends to diminish as pretraining progresses. Lightweight fine-tuning substantially restores linearity, reducing divergence between the predicted distribution and the average of the separate distributions. A guided decoding procedure then disentangles the superposed output so two coherent continuations can be generated from one forward pass.
- Linearly mixed text streams produce a superposition of individual next-token distributions.
- Superposition appears intrinsic to Transformers and weakens as pretraining progresses.
- Lightweight fine-tuning substantially restores linearity versus averaged token distributions.
- Guided decoding generates two coherent continuations from a single forward pass.
From the original article
1 min read at huggingface.co
While Large Language Models (LLMs) rely on highly non-linear components, in this work we demonstrate that they exhibit fundamental linearity: when inputs from distinct text streams are linearly combined, the model outputs a superposition of the individual next-token distributions. We term this the Superposition Linearity Hypothesis.
By Pavel Tikhonov, Anton Korznikov, Matvey Mikhalchuk · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.