Better version of the monthly Twitter thread. Emergent and Predictable Memorization in Large Language Models Memorization in LLMs is a practical issue: it is both a privacy and a copyright disaster. It is also an important research direction in both machine learning and AI safety; in a sense, memorization is the complement of generalization.
April 2023 safety news: Supervising AIs improving AIs, LLM memorization, OpinionQA
April 2023 safety news: Supervising AIs…
April 2023 safety news: Supervising AIs improving AIs, LLM memorization, OpinionQA
Better version of the monthly Twitter thread. Emergent and Predictable Memorization in Large Language Models Memorization in LLMs is a practical issue: it is both a privacy and a copyright disaster. It is also an important research direction in both machine learning and AI safety; in a sense, memorization is the complement of generalization.