Abhimanyu Hans

Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs

2024 · arXiv (Cornell University)

Large language models can memorize and repeat their training data, causing privacy and copyright risks. To mitigate memorization, we introduce a subtle modification to the next-token training objective that we call the goldfish loss. During …

Has My System Prompt Been Used? Large Language Model Prompt Membership Inference

2025 · arXiv (Cornell University)

Prompt engineering has emerged as a powerful technique for optimizing large language models (LLMs) for specific applications, enabling faster prototyping and improved performance, and giving rise to the interest of the community in protecting proprietary …