83 citations · 101 across the 10 of their papers we have counts for
4 papers · 1 filter
Playing Whack-a-Mole with misconceptions about memorization, extraction, and copyright
A. Feder Cooper
After careful review, I'm confident the headline fine-tuning memorization results in Alignment Whack-a-Mole use an invalid measurement procedure. The book memorization coverage met…
Probabilistic "Copies" in Generative AI Models
Mark A. Lemley, A. Feder Cooper
Recent work shows that it is possible to extract verbatim or near-verbatim text of some copyrighted works from some large language models (LLMs or models). That is evidence that th…
Extractable Memorization From First Principles
A. Feder Cooper, Marika Swanberg, Jamie Hayes +6
Recent work on extractable memorization in language models suffers from two contrasting validity problems. Some studies overstate extraction, for example, by using sequences too sh…
Estimating near-verbatim extraction risk in language models with decoding-constrained beam search
A. Feder Cooper, Mark A. Lemley, Christopher De Sa +6
Recent work shows that standard greedy-decoding extraction methods for quantifying memorization in LLMs miss how extraction risk varies across sequences. Probabilistic extraction -…