Ryan Cotterell

Transducing Language Models

Transformers are Inherently Succinct

Context-free Recognition with Transformers

Optimizing Language Models for Crosslingual Knowledge Consistency

Probability Distributions Computed by Autoregressive Transformers

Empirically Testing Expressivity Bounds for Neural Network Architectures

Measuring Scarcity–Complexity Collision in Language Model Estimation

Bearing Syntactic Fruit with Stack-Augmented Neural Networks

Which Formal Languages Can Large Language Models Learn in Context?

Rational Irrationality: Evaluating LLMs In Games With Strategic Behavior Discrepancies

It Depends: Understanding Why Models Struggle with Long-Range Dependencies

Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo

Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling

Language Models over Canonical Byte-Pair Encodings

Characterizing the Expressivity of Fixed-Precision Transformer Language Models

Better Estimation of the Kullback--Leibler Divergence Between Language Models

Are Language Models Efficient Reasoners? A Perspective from Logic Programming

Controllable Context Sensitivity and the Knob Behind It

Gumbel Counterfactual Generation From Language Models

The Foundations of Tokenization: Statistical and Computational Concerns

Training Neural Networks as Recognizers of Formal Languages

From Language Models over Tokens to Language Models over Characters

Variational Best-of-N Alignment

A Causal Study on The Learnability of Formal Languages