Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Fragments to Facts: Partial-Information Fragment Inference from LLMs
Lucas Rosenblatt, Bin Han, Robert Wolfe +1
Large language models (LLMs) can leak sensitive training data through memorization and membership inference attacks. Prior work has primarily focused on strong adversarial assumpti…
cs.LG2024
Laboratory-Scale AI: Open-Weight Models are Competitive with ChatGPT Even in Low-Resource Settings
Robert Wolfe, Isaac Slaughter, Bin Han +8
The rapid proliferation of generative AI has raised questions about the competitiveness of lower-parameter, locally tunable, open-weight models relative to high-parameter, API-guar…