Book-level memorization varies sharply across LLMs: most books escape most models, yet Llama 3.1 70B can reproduce Harry Potter almost entirely from a six-token seed prompt.
Faber & Faber Ltd; William Morrow
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Extracting memorized pieces of (copyrighted) books from open-weight language models
Book-level memorization varies sharply across LLMs: most books escape most models, yet Llama 3.1 70B can reproduce Harry Potter almost entirely from a six-token seed prompt.