LLMs and Contextual Integrity
Bruce Schneier highlights two papers: the CIMemories benchmark shows frontier LLMs leak memory attributes up to 69%, and an RL method reduces inappropriate disclosures.
4
1 stories, newest first · one card per story
Bruce Schneier highlights two papers: the CIMemories benchmark shows frontier LLMs leak memory attributes up to 69%, and an RL method reduces inappropriate disclosures.
Today 1.1K readers · 1.6K views · 1.2K reads · all time 159K views