Paraphrase and Solve: Exploring and Exploiting the Impact of Surface Form on Mathematical Reasoning in Large Language Models

Can You Learn Semantics Through Next-Word Prediction? The Case of Entailment

Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning

What Do Language Models Hear? Probing for Auditory Representations in Language Models

The Surprising Effectiveness of Test-Time Training for Few-Shot Learning

In-Context Language Learning: Architectures and Algorithms

Data Engineering for Scaling Language Models to 128K Context

Parallelizing Linear Transformers with the Delta Rule over Sequence Length

Training-Free Activation Sparsity in Large Language Models

The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities