Controlling the Extraction of Memorized Data from Large Language Models via Prompt-Tuning
Research paper by Mustafa Safa Ozdayi and collaborators. Published 2023-05-19. Topics: prompt-tuning, extraction rates, memorized content, LLMs, GPT-Neo.
Resource information
- Authors
- Mustafa Safa Ozdayi, Charith Peris, Jack FitzGerald, Christophe Dupuy, Jimit Majmudar, Haidar Khan, Rahil Parikh, Rahul Gupta
- Research topics
- prompt-tuning, extraction rates, memorized content, LLMs, GPT-Neo, perplexity, privacy-utility trade-offs
- Publication date
- 2023-05-19
- Publication
- arXiv
- Last record update
- Nov 3, 2026