7 papers
Human-AI Teaming Through the Lens of Calibration
Eric Nalisnick, Chi Zhang, Sophia Qian +1
We study models for human-AI teaming through the lens of statistical calibration. We assume the team consists of an AI model and human -- both of which are calibrated with respect…
Data-Constrained Language Model Pretraining: Improved Regularization and Scaling Laws
Zhiwei Xu, Shihao Wu, Hanseul Cho +2
Classical scaling laws for language model pretraining balance model size against training dataset size under a fixed compute budget, assuming abundant data and a single pass over t…
Discrete Causal Representation Learning
Wenjin Zhang, Yixin Wang, Yuqi Gu
Causal representation learning seeks to uncover causal relationships among high-level latent variables from low-level, entangled, and noisy observations. Existing approaches often…
Latency-Response Theory Model: Evaluating Large Language Models via Response Accuracy and Chain-of-Thought Length
Zhiyu Xu, Jia Liu, Yixin Wang +1
The proliferation of Large Language Models (LLMs) necessitates valid evaluation methods to provide guidance for both downstream applications and actionable future improvements. The…
Last Layer Empirical Bayes
Valentin Villecroze, Yixin Wang, Gabriel Loaiza-Ganem
The task of quantifying the inherent uncertainty associated with neural network predictions is a key challenge in artificial intelligence. Bayesian neural networks (BNNs) and deep…
Deep Generative Models: Complexity, Dimensionality, and Approximation
Kevin Wang, Hongqian Niu, Yixin Wang +1
Generative networks have shown remarkable success in learning complex data distributions, particularly in generating high-dimensional data from lower-dimensional inputs. While this…