activity
20242026
most citedSymmetry in language statistics shapes the geometry of model representations

1 citations · 1 across the 3 of their papers we have counts for

collaborators

8 papers

cs.LG20261 cited

Symmetry in language statistics shapes the geometry of model representations

Dhruva Karkada, Daniel J. Korchinski, Andres Nava +2

The internal representations learned by language models consistently exhibit striking geometric structure: calendar months organize into a circle, historical years form a smooth on…

cs.LG2026

Neuron Populations Exhibit Divergent Selectivity with Scale

Amil Dravid, Yasaman Bahri, Alexei A. Efros +1

We investigate whether neuron populations within neural networks evolve predictably with scale, extending scaling laws beyond macroscopic observables such as loss. To probe this qu…

cs.CL2026

Context Structure Reshapes the Representational Geometry of Language Models

Eghbal A. Hosseini, Yuxuan Li, Yasaman Bahri +2

Large Language Models (LLMs) have been shown to organize the representations of input sequences into straighter neural trajectories in their deep layers, which has been hypothesize…

cs.CL2025

On the Emergence of Linear Analogies in Word Embeddings

Daniel J. Korchinski, Dhruva Karkada, Yasaman Bahri +1

Models such as Word2Vec and GloVe construct word embeddings based on the co-occurrence probability of words and in text corpora. The resulting vectors not on…

cs.LG2025

Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models

Dhruva Karkada, James B. Simon, Yasaman Bahri +1

Self-supervised word embedding algorithms such as word2vec provide a minimal setting for studying representation learning in language modeling. We examine the quartic Taylor approx…

cs.CL2025

CURIE: Evaluating LLMs On Multitask Scientific Long Context Understanding and Reasoning

Hao Cui, Zahra Shamsi, Gowoon Cheon +31

Scientific problem-solving involves synthesizing information while applying expert knowledge. We introduce CURIE, a scientific long-Context Understanding,Reasoning and Information…