activity
20232026
most citedScalable Extraction of Training Data from (Production) Language Models

83 citations · 101 across the 10 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

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 -…