Challenge: Neural networks offer good approximation to many tasks but fail to reach perfect generalization.
Approach: They propose to use a formal language to test whether a theoretically correct solution is not an optimum of commonly used objectives.
Outcome: The proposed model fails to reach the theoretically correct solution even with regularization techniques.

Similar Papers

Minimum Description Length Recurrent Neural Networks (2022.tacl-1)

Copied to clipboard

Challenge: We show that neural networks that optimize a minimum description length score master memory challenges and perform addition with 100% accuracy.
Approach: They train neural networks to optimize a Minimum Description Length score . they show that they master tasks involving memory challenges and perform addition .
Outcome: The proposed models master languages and perform addition with 100% accuracy . they show that they can generalize from small training corpora and large training corpus .
Computational Expressivity of Neural Language Models (2024.acl-tutorials)

Copied to clipboard

Challenge: Language models (LMs) are at the forefront of NLP research due to their versatility across diverse tasks.
Approach: This tutorial will provide a framework for formal analysis of modern language models using tools from formal language theory.
Outcome: This tutorial will provide a framework for formal analysis of modern language models using tools from formal language theory (FLT).
The Learnability of Model-Theoretic Interpretation Functions in Artificial Neural Networks (2026.findings-acl)

Copied to clipboard

Challenge: Entity vectors improve scores on basic event, while gated architectures benefit most.
Approach: They extend entity-level semantic representations, modern architectures, principled competing event generation, extended systematicity tests and a two-dimensional difficulty analysis disaggregating results by modifier complexity.
Outcome: The proposed model-theoretic interpretation functions generalize systematically to out-of-training-sample sentences.
Lower Bounds on the Expressivity of Recurrent Neural Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Recent studies of the representational capacity of neural LMs have focused on their ability to recognize formal languages.
Approach: They propose to connect recurrent neural networks (RNNs) as classifiers to finite-state automatas (FSAs) and a probabilistic FSA to characterize their representational capacity.
Outcome: The proposed models can express arbitrary regular LMs with linearly bounded precision.
On Efficiently Representing Regular Languages as RNNs (2024.findings-acl)

Copied to clipboard

Challenge: Recent work by Hewitt et al. (2020) provides an interpretation of the empirical success of recurrent neural networks (RNNs) as language models (LMs).
Approach: They generalize their construction and show that RNNs can efficiently represent a larger class of LMs than previously claimed.
Outcome: The results suggest that RNNs can represent a larger class of LMs than previously claimed .
Heterogeneity in Formal Linguistic Competence of Language Models: Is Data the Real Bottleneck? (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) exhibit a puzzling disparity in their formal linguistic competence, even after training on trillions of tokens.
Approach: They pre-train Large Language Models on 100M-token corpora and inject a minimal amount of synthetic data targeting specific linguistic phenomena into the model.
Outcome: The proposed intervention significantly improves model performance in 8 out of the 9 worst-performing BLiMP paradigms.
A Systematic Assessment of Syntactic Generalization in Neural Language Models (2020.acl-main)

Copied to clipboard

Challenge: Existing work on syntactic knowledge models has not provided a clear picture of the properties required to produce proper syntaktic generalizations.
Approach: They propose to evaluate syntactic knowledge of language models by varying model architectures . they find substantial differences in syntaktic generalization performance by model architecture .
Outcome: The proposed model architectures outperform other architectures on a set of 34 English-language syntactic test suites.
From Informal to Formal – Incorporating and Evaluating LLMs on Natural Language Requirements to Verifiable Formal Proofs (2025.acl-long)

Copied to clipboard

Challenge: Recent studies in formal mathematical reasoning have shown an unstoppable growth trend.
Approach: They constructed 18k high-quality instruction-response pairs across five mainstream formal specification languages and evaluated them against ten open-sourced LLMs.
Outcome: The proposed model compared instruction-response pairs across five formal specification languages and found that the LLMs were good at writing proof segments when given either the code, or the detailed description of proof steps.
Probing Linguistic Systematicity (2020.acl-main)

Copied to clipboard

Challenge: Existing evidence that deep natural language understanding models do not learn systematically is lacking.
Approach: They examine whether deep natural language understanding models exhibit systematicity . they find that network architectures can generalize non-systematically .
Outcome: The proposed model generalizes non-systematically, but is unsatisfactory, the authors argue . they show that the current state-of-the-art models do not generalize systematically .
Do Neural Models Learn Systematicity of Monotonicity Inference in Natural Language? (2020.acl-main)

Copied to clipboard

Challenge: Despite the success of language models using neural networks, it remains unclear to what extent neural models have the generalization ability to perform inferences.
Approach: They propose a method to evaluate whether neural models can learn systematicity of monotonicity inference in natural language.
Outcome: The proposed method shows that neural models can perform inferences on unseen combinations of lexical and logical phenomena when syntactic structures are similar between training and test sets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations