Picture for Katherine Lee

Katherine Lee

Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon

Add code
Jun 25, 2024
Viaarxiv icon

LMD3: Language Model Data Density Dependence

Add code
May 10, 2024
Viaarxiv icon

Gemma: Open Models Based on Gemini Research and Technology

Add code
Mar 13, 2024
Figure 1 for Gemma: Open Models Based on Gemini Research and Technology
Figure 2 for Gemma: Open Models Based on Gemini Research and Technology
Figure 3 for Gemma: Open Models Based on Gemini Research and Technology
Figure 4 for Gemma: Open Models Based on Gemini Research and Technology
Viaarxiv icon

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Add code
Mar 08, 2024
Viaarxiv icon

Gemini: A Family of Highly Capable Multimodal Models

Add code
Dec 19, 2023
Viaarxiv icon

Scalable Extraction of Training Data from (Production) Language Models

Add code
Nov 28, 2023
Viaarxiv icon

Reverse-Engineering Decoding Strategies Given Blackbox Access to a Language Generation System

Add code
Sep 09, 2023
Viaarxiv icon

MADLAD-400: A Multilingual And Document-Level Large Audited Dataset

Add code
Sep 09, 2023
Viaarxiv icon

Are aligned neural networks adversarially aligned?

Add code
Jun 26, 2023
Viaarxiv icon

A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity

Add code
May 22, 2023
Viaarxiv icon