activity
20232026
most citedMachine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research

2 citations · 2 across the 2 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 -…