paperdive
.ai
About
Episodes
Concepts
Lit Review
Glossary
Listen
Concept · 1 episode(s)
Context Leakage
← all concepts
Episodes covering this
246
160 Perfect Refusals, And The Refusals Were The Leak
Inadvertent Context Leakage in Language Models
Fairoze, Mangaokar, Chaudhuri et al. · University of California
·
20 min
·
Aug 21, 2026
Worth reading next
Papers we haven't done a deep dive on yet, but would recommend on this topic.
Extracting Training Data from Large Language Models
Are Large Pre-Trained Language Models Leaking Your Personal Information?