Pith. sign in

REVIEW 8 cited by

Neural Networks and the Chomsky Hierarchy

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 2207.02098 v3 pith:ZQDB6A7E submitted 2022-07-05 cs.LG cs.AIcs.CLcs.FL

classification cs.LGcs.AIcs.CLcs.FL
keywords tasksgeneralizegeneralizationnetworksneuralchomskydataextensive
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Reliable generalization lies at the heart of safe ML and AI. However, understanding when and how neural networks generalize remains one of the most important unsolved problems in the field. In this work, we conduct an extensive empirical study (20'910 models, 15 tasks) to investigate whether insights from the theory of computation can predict the limits of neural network generalization in practice. We demonstrate that grouping tasks according to the Chomsky hierarchy allows us to forecast whether certain architectures will be able to generalize to out-of-distribution inputs. This includes negative results where even extensive amounts of data and training time never lead to any non-trivial generalization, despite models having sufficient capacity to fit the training data perfectly. Our results show that, for our subset of tasks, RNNs and Transformers fail to generalize on non-regular tasks, LSTMs can solve regular and counter-language tasks, and only networks augmented with structured memory (such as a stack or memory tape) can successfully generalize on context-free and context-sensitive tasks.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 45 citations worldwide. Full citation record

  1. Auditing Discovery Claims: A Two-Sided Criterion for Agentic Science, with the Negative Side Decidable

    cs.AI 2026-08 conditional novelty 7.0 of 10

    A two-sided audit with a formally decidable negative side shows a single-oracle RNA design claim collapses from 43/60 to 1/60 under a three-predictor panel, while two AI-written operators survive a held-out judge.

  2. When Does Reward Teach State? A Hidden-Automaton Instrument and the Group-Language Boundary

    cs.LG 2026-07 conditional novelty 7.0 of 10

    High reward in sparse RL does not imply latent-state recovery; a hidden-DFA instrument separates perception from planning gaps and flags group-language structure as a pre-training warning.

  3. Learning State-Tracking from Code Using Linear RNNs

    cs.LG 2026-02 unverdicted novelty 7.0 of 10

    Linear RNNs with negative eigenvalues track permutation state from REPL traces under next-token prediction, but probabilistic state-tracking with partial reveals forces exponential belief decay without nonlinear renor...

  4. (How) Can Transformers Predict Pseudo-Random Numbers?

    cs.LG 2025-02 conditional novelty 7.0 of 10

    Transformers predict LCG sequences in-context for fixed moduli up to 2^32 and unseen moduli up to 2^16 by learning the modulus factorization and digit-wise periodic structure.

  5. Rethinking Memorization Measures and their Implications in Large Language Models

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Contextual memorization, defined by comparing a string's training loss against the best loss without training on that string, is stricter than counterfactual memorization and suggests that zero-memorization optimal le...

  6. Hierarchical Solomonoff Induction: An Unbounded Machine Learning Model

    cs.LG 2026-08 conditional novelty 5.0 of 10

    HSI, a hyperprior over all Solomonoff priors, is shown equivalent to Solomonoff Induction while enabling dataset-conditioned prediction and a training-set error bound.

  7. Pause Tokens Strictly Increase the Expressivity of Constant-Depth Transformers

    cs.LG 2025-05 reject novelty 5.0 of 10

    The paper claims pause tokens strictly increase constant-precision, constant-depth Transformer expressivity from a subset of AC0 to AC0 (and log-precision to TC0), but the constant-precision proof is not sound as written.

  8. Tokenization Constraints in LLMs: A Study of Symbolic and Arithmetic Reasoning Limits

    cs.CL 2025-05 conditional novelty 5.0 of 10

    Matching token boundaries to the atomic units of a task, such as one letter per token, can improve LLM accuracy on symbolic reasoning by tens of percentage points and may matter more than model size.

Pith tools