12 citations · 29 across the 7 of their papers we have counts for
8 papers
Understanding and Mitigating Role Spoofing in LLMs
Ezra Edelman, Benjamin Edelman, Surbhi Goel +1
Despite growing capabilities, LLMs remain susceptible to prompt injections: malicious inputs that can manipulate or hijack models. In particular, it has recently been observed that…
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…
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…
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…
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…
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…
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…
Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit
Boaz Barak, Benjamin L. Edelman, Surbhi Goel +3
There is mounting evidence of emergent phenomena in the capabilities of deep learning methods as we scale up datasets, model sizes, and training times. While there are some account…