most citedDistinguishing the Knowable from the Unknowable with Language Models

3 citations · 4 across the 3 of their papers we have counts for

collaborators

6 papers

cs.LG2024

Transcendence: Generative Models Can Outperform The Experts That Train Them

Edwin Zhang, Vincent Zhu, Naomi Saphra +5

Generative models are trained with the simple objective of imitating the conditional probability distribution induced by the data they are trained on. Therefore, when trained on da…

cs.LG20243 cited

Distinguishing the Knowable from the Unknowable with Language Models

Gustaf Ahdritz, Tian Qin, Nikhil Vyas +2

We study the feasibility of identifying epistemic uncertainty (reflecting a lack of knowledge), as opposed to aleatoric uncertainty (reflecting entropy in the underlying distributi…

cs.LG20241 cited

The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains

Benjamin L. Edelman, Ezra Edelman, Surbhi Goel +2

Large language models have the ability to generate text that mimics patterns in their inputs. We introduce a simple Markov Chain sequence modeling task in order to study how this i…

cs.LG2023

Feature emergence via margin maximization: case studies in algebraic tasks

Depen Morwani, Benjamin L. Edelman, Costin-Andrei Oncescu +2

Understanding the internal representations learned by neural networks is a cornerstone challenge in the science of machine learning. While there have been significant recent stride…

cs.LG2023

Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models

Hanlin Zhang, Benjamin L. Edelman, Danilo Francati +3

Watermarking generative models consists of planting a statistical signal (watermark) in a model's output so that it can be later verified that the output was generated by the given…

cs.LG2023

Pareto Frontiers in Neural Feature Learning: Data, Compute, Width, and Luck

Benjamin L. Edelman, Surbhi Goel, Sham Kakade +2

In modern deep learning, algorithmic choices (such as width, depth, and learning rate) are known to modulate nuanced resource tradeoffs. This work investigates how these complexiti…