Pith. sign in

REVIEW 4 cited by

On Limitations of the Transformer Architecture

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 2402.08164 v2 pith:UFXXH6BV submitted 2024-02-13 stat.ML cs.AIcs.LG

On Limitations of the Transformer Architecture

classification stat.ML cs.AIcs.LG
keywords largecomplexitydomainsenoughfunctionsllmstaskstransformer
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

What are the root causes of hallucinations in large language models (LLMs)? We use Communication Complexity to prove that the Transformer layer is incapable of composing functions (e.g., identify a grandparent of a person in a genealogy) if the domains of the functions are large enough; we show through examples that this inability is already empirically present when the domains are quite small. We also point out that several mathematical tasks that are at the core of the so-called compositional tasks thought to be hard for LLMs are unlikely to be solvable by Transformers, for large enough instances and assuming that certain well accepted conjectures in the field of Computational Complexity are true.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

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

  1. When Does In-Context Search Help? A Sampling-Complexity Theory of Reflection-Driven Reasoning

    cs.AI 2026-07 conditional novelty 7.0

    When reflections localize early errors, in-context search solves exp-small pass-rate problems with poly sequential attempts; otherwise it offers no asymptotic gain over parallel sampling, and the update is learnable a...

  2. How Much Cache Does Reasoning Need? Depth-Cache Tradeoffs in KV-Compressed Transformers

    cs.LG 2026-04 unverdicted novelty 7.0

    Transformers need depth scaling as the product of ceil(k/s) and log n terms for k-hop pointer chasing under cache size s, with a conjectured lower bound, proved upper bound via windowed pointer doubling, and an adapti...

  3. GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models

    cs.LG 2024-10 accept novelty 7.0

    LLMs display high variance and major accuracy drops on GSM-Symbolic variants of grade-school math problems, indicating they replicate training patterns rather than execute logical reasoning.

  4. Lost in Cultural Translation: Do LLMs Struggle with Math Across Cultural Contexts?

    cs.AI 2025-03 conditional novelty 5.0

    LLMs show accuracy drops of 0.3% to 5.9% on GSM8K math problems when culturally adapted to six countries while keeping math operations identical, with statistical significance confirmed by McNemar tests.