Search

Anej Svete

Gumbel Counterfactual Generation from Language Models
Information Locality as an Inductive Bias for Neural Language Models
Probability Distributions Computed by Hard-Attention Transformers
Training Neural Networks as Recognizers of Formal Languages
Unique Hard Attention: A Tale of Two Sides
On Affine Homotopy between Language Encoders
A Probability--Quality Trade-off in Aligned Language Models and its Relation to Sampling Adaptors
An L* Algorithm for Deterministic Weighted Automata
Can Transformer Language Models Learn $n$-gram Language Models?
On Efficiently Representing Regular Languages as RNNs
Transformers Can Represent n-gram Language Models
Lower Bounds on the Expressivity of Recurrent Neural Language Models
On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning
The Role of $n$-gram Smoothing in the Age of Neural Networks
What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages
On the Representational Capacity of Recurrent Neural Language Models
Recurrent Neural Language Models as Probabilistic Finite-state Automata
Algorithms for Weighted Finite-State Automata with Failure Arcs