arXiv Computation and Language August 27, 2026 By Christo Kirov, Ryan Cotterell

Recurrent Neural Networks in Linguistic Theory: Revisiting Pinker and Prince (1988) and the Past Tense Debate

Read the original on arXiv Computation and Language →

The Flow has not summarised this story yet — read it at arXiv Computation and Language.

arXiv AI

Jul 22

For What Reason? Interpreting Models' Encoding of Causation and Antithesis

arXiv:2607. 18570v1 Announce Type: cross Abstract: Discourse relations provide document structure, critical to language understanding and enabling language model performance and ethicality.

By Abhidip Bhattacharyya, Shira Wein

llms safety

arXiv Machine Learning

Jun 2

A Pre-Training Analogue of Grokking in Language Models: Tracing Delayed Grammatical Generalization

arXiv:2606. 00230v1 Announce Type: new Abstract: Grokking, the phenomenon in which neural networks generalize long after fitting their training data, has been studied in supervised settings on many epochs.

By Sherin Muckatira, Namrata Shivagunde, Vijeta Deshpande, Anna Rumshisky

llms

arXiv AI

Aug 17

A Unified Assessment of the Poverty of the Stimulus Argument for Neural Language Models

arXiv:2602. 09992v2 Announce Type: replace-cross Abstract: Several recent contributions have evaluated the Poverty of the Stimulus Hypothesis (PoSH) using Artificial Neural Networks (ANNs).

By Xiulin Yang, Arianna Bisazza, Nathan Schneider, Ethan Gotlieb Wilcox

llms benchmarks

arXiv Machine Learning

Aug 18

Do Language Models Consistently Encode the Current Year?

arXiv:2608. 15507v1 Announce Type: cross Abstract: A consistent concept of the current time is important for temporal reasoning, yet how language models represent the current time is not well understood.

By Suze van Adrichem, Aditi Bhaskar, Diyi Yang, Christopher Potts, Jing Huang

llms fine-tuning

arXiv AI

Aug 7

Beyond Sequence Order: Syntax-Informed Positional Embeddings for Transformers

arXiv:2608. 06111v1 Announce Type: cross Abstract: Positional embeddings (PE) in Transformers encode token distance and order but are largely agnostic to \textit{syntactic structure}.

By Haris Riaz, Hyungji Kim, Mihai Surdeanu

llms rag benchmarks

arXiv AI

Aug 21

When Machines Speak: A Unified Generative Framework for Integrating Machine-Native Symbols into Pretrained Large Language Models

arXiv:2608. 19529v1 Announce Type: cross Abstract: Many real-world AI systems represent entities, behaviors, and structured information using discrete machine-native symbols rather than natural language.

By Su Yan, Rakesh Iyer

llms rag

One email a morning, machine-written

Related stories

For What Reason? Interpreting Models' Encoding of Causation and Antithesis

A Pre-Training Analogue of Grokking in Language Models: Tracing Delayed Grammatical Generalization

A Unified Assessment of the Poverty of the Stimulus Argument for Neural Language Models

Do Language Models Consistently Encode the Current Year?

Beyond Sequence Order: Syntax-Informed Positional Embeddings for Transformers

When Machines Speak: A Unified Generative Framework for Integrating Machine-Native Symbols into Pretrained Large Language Models