로그인
통찰 - Memorization Analysis in LLMs
Memorization Insights from Large Language Models: ROME Study
The author explores memorization in large language models through a novel approach named ROME, focusing on disparities between memorized and non-memorized samples using text, probability, and hidden state insights.
Uncovering Memorization in Instruction-Tuned LLMs
Instruction-tuned models exhibit higher levels of memorization than base models when prompted with instruction-based prompts, challenging prior assumptions.
