arxiv
PublishedJuly 22, 2026 at 4:00 AM
Estimating near-verbatim extraction risk in language models with decoding-constrained beam search
Publisher summary· verbatim
arXiv:2603.24917v2 Announce Type: replace Abstract: Recent work shows that standard greedy-decoding extraction methods for quantifying memorization in LLMs miss how extraction risk varies across sequences. Probabilistic extraction -- computing the probability of generating a target suffix given a pr
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivDBMol: Design of High-Affinity, Target-Specific Small Molecules through Structure Prediction Models5harxivHPD-Parsing: Hierarchical Parallel Document Parsing5harxivIncomplete Observations Boost Evolutionary Performance in Ocean Modeling5harxivCalibrated Selective Fact-Checking via Evidence Chain Evaluation5hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗