Geometric Structure of Layer Updates in Deep Language Models
Explore the geometric structure of layer updates in deep language models and their impact on model performance and architecture.
LLMs in Behavioral Simulation: Accurate Descriptions, Flawed Causal Effects
Explore how large language models simulate behavior accurately but struggle with causal effect fidelity in interventions across diverse populations.
Skeleton-Based Narrative Coherence Modeling in NLP
Explore skeleton-based methods in NLP for improving narrative coherence using the Sentence/Skeleton Similarity Network (SSN) framework.
Are Frontier Models Essential for Verifying Math Proofs?
Explore if frontier AI models are necessary for accurate mathematical proof verification and how smaller models can match their performance.
Deep Learning for Diabetic Retinopathy: Dataset Insights
Explore how deep learning and quality datasets improve diabetic retinopathy detection, grading, and screening for better patient outcomes.