Pith. sign in

REVIEW 2 cited by

Transformers need glasses! Information over-squashing in language tasks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.04267 v2 pith:W6VAQRNZ submitted 2024-06-06 cs.CL cs.LG

classification cs.CLcs.LG
keywords languagellmstransformeranalysisdecoder-onlyfinalinformationmodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We study how information propagates in decoder-only Transformers, which are the architectural backbone of most existing frontier large language models (LLMs). We rely on a theoretical signal propagation analysis -- specifically, we analyse the representations of the last token in the final layer of the Transformer, as this is the representation used for next-token prediction. Our analysis reveals a representational collapse phenomenon: we prove that certain distinct sequences of inputs to the Transformer can yield arbitrarily close representations in the final token. This effect is exacerbated by the low-precision floating-point formats frequently used in modern LLMs. As a result, the model is provably unable to respond to these sequences in different ways -- leading to errors in, e.g., tasks involving counting or copying. Further, we show that decoder-only Transformer language models can lose sensitivity to specific tokens in the input, which relates to the well-known phenomenon of over-squashing in graph neural networks. We provide empirical evidence supporting our claims on contemporary LLMs. Our theory also points to simple solutions towards ameliorating these issues.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. You Do Not Fully Utilize Transformer's Representation Capacity

    cs.LG 2025-02 conditional novelty 5.0 of 10

    Adding learned per-head routing over previous layers' key-value buffers to a Transformer reduces representation collapse, lowers language modeling loss, and improves synthetic arithmetic and planning accuracy.

  2. Position: The Future of Bayesian Prediction Is Prior-Fitted

    cs.LG 2025-05 conditional novelty 4.0 of 10

    PFNs, which amortize Bayesian inference by training on datasets sampled from a prior, are likely to supersede MCMC and variational inference for most prediction tasks, the authors argue.

Pith tools