Jackson Petty

Low-resource languages pose a challenge for machine translation with large language models (LLMs), which require large amounts of training data.

This course is an introductory survey of linguistics—the scientific study of language.

Large language models (LLMs) are increasingly used to solve complex tasks where they must retrieve and compose many pieces of in-context information in long reasoning chains.

Yiddish possesses a class of ‘inseparable’ verbal prefixes which augment the meaning of the verbs they attach to.

Ranking foods by protein efficiency.

Would you press it?

Pretraining language models on formal languages can improve their acquisition of natural language, but it is unclear which features of the formal language impart an inductive bias that leads to effective transfer.

Large language models are increasingly trained on corpora containing both natural language and non-linguistic data like source code.

We present GPQA, a challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry.

This work examines artificial neural language model behavior through the lens of morphological productivity.

State-space models (SSMs) have emerged as a potential alternative architecture for building large language models (LLMs) compared to the previously ubiquitous transformer architecture.

Since at least the proposal of the Turing test, building computational systems that can communicate with humans using natural language has been a central goal for Al research.

In-context learning (ICL) is now a common method for supervising large language models (LLMs): given labeled examples in the input context, the LLM learns to perform the task without weight updates.

As AI systems are used to answer more difficult questions and potentially help create new knowledge, judging the truthfulness of their outputs becomes more difficult and more important.

Language models are typically evaluated on their success at predicting the distribution of specific words in specific contexts.

To process novel sentences, language models (LMs) must generalize compositionally – combine familiar elements in new ways.

Naturally occurring information-seeking questions often contain questionable assumptions—assumptions that are false or unverifiable.

The hexagon is the least-perimeter tile in the Euclidean plane for any given area.

Ingredients: two API calls and a server; Time: 1hr; Serves anonymized DMs to facilitate asynchronous data collection.

How is knowledge of position-role mappings in natural language learned?

To learn an unbounded problem is to generalize well from a limited set of training data.

A brief reflection on the roots of sacrifice for Pesach.

In 2008 Reichardt proved that the optimal Euclidean double bubble—the least-perimeter way to enclose and separate two given volumes—is three spherical caps meeting along a sphere at $120$ degrees.

Natural language exhibits patterns of hierarchically governed dependencies, in which relations between words are sensitive to syntactic structure rather than linear ordering.

The hexagon is the least-perimeter tile in the Euclidean plane.

Reflexive anaphora present a challenge for semantic interpretation: their meaning varies depending on context in a way that appears to require abstract variables.