Search Results for author:
Found 9 papers, 3 papers with code
Foundational Challenges in Assuring Alignment and Safety of Large Language Models
This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs).
The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains
We examine how learning is affected by varying the prior distribution over Markov chains, and consider the generalization of our in-context learning of Markov chains (ICL-MC) task to $n$-grams for $n > 2$.
Distinguishing the Knowable from the Unknowable with Language Models
We study the feasibility of identifying epistemic uncertainty (reflecting a lack of knowledge), as opposed to aleatoric uncertainty (reflecting entropy in the underlying distribution), in the outputs of large language models (LLMs) over free-form text.
Feature emergence via margin maximization: case studies in algebraic tasks
Understanding the internal representations learned by neural networks is a cornerstone challenge in the science of machine learning.
Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models
To prove this result, we introduce a generic efficient watermark attack; the attacker is not required to know the private key of the scheme or even which scheme is used.
Pareto Frontiers in Neural Feature Learning: Data, Compute, Width, and Luck
Finally, we show that the synthetic sparse parity task can be useful as a proxy for real problems requiring axis-aligned feature learning.
Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit
There is mounting evidence of emergent phenomena in the capabilities of deep learning methods as we scale up datasets, model sizes, and training times.
Inductive Biases and Variable Creation in Self-Attention Mechanisms
Self-attention, an architectural motif designed to model long-range interactions in sequential data, has driven numerous recent breakthroughs in natural language processing and beyond.
SGD on Neural Networks Learns Functions of Increasing Complexity
We perform an experimental study of the dynamics of Stochastic Gradient Descent (SGD) in learning deep neural networks for several real and synthetic classification tasks.
