5 papers
How Much Structure Do LLMs Need? Evaluating LLMs for Bibliometric Cluster Description
Abraham Camelo-Guerrero, Jairo Diaz-Rodriguez
Large language models (LLMs) can support scientific literature synthesis, but remain prone to hallucinated references, uneven coverage, and weakly grounded thematic organization. W…
Inheritance Between Feedforward and Convolutional Networks via Model Projection
Nicolas Ewen, Jairo Diaz-Rodriguez, Kelly Ramsay
Neural-network techniques are often transferred across architecture families by analogy, but such transfer is valid only when the assumptions required by a technique are preserved.…
The Curved Spacetime of Transformer Architectures
Riccardo Di Sipio, Jairo Diaz-Rodriguez, Luis Serrano
We present a geometric framework for understanding Transformer-based language models, drawing an explicit analogy to General Relativity. Queries and keys induce an effective metric…
Dynamics of Spontaneous Topic Changes in Next Token Prediction with Self-Attention
Mumin Jia, Jairo Diaz-Rodriguez
Human cognition is punctuated by abrupt, spontaneous shifts between topics-driven by emotional, contextual, or associative cues-a phenomenon known as spontaneous thought in neurosc…
Differentially Private Boxplots
Kelly Ramsay, Jairo Diaz-Rodriguez
Despite the potential of differentially private data visualization to harmonize data analysis and privacy, research in this area remains underdeveloped. Boxplots are a widely popul…