Rethinking llm memorization through the lens of adversarial compression

A Schwarzschild, Z Feng, P Maini, ZC Lipton… - arXiv preprint arXiv …, 2024 - arxiv.org
Large language models (LLMs) trained on web-scale datasets raise substantial concerns
regarding permissible data usage. One major question is whether these models" memorize" …
被引用次数：22 相关文章

Rethinking LLM Memorization through the Lens of Adversarial Compression

A Schwarzschild, Z Feng, P Maini, ZC Lipton… - arXiv e …, 2024 - ui.adsabs.harvard.edu
Large language models (LLMs) trained on web-scale datasets raise substantial concerns
regarding permissible data usage. One major question is whether these models" memorize" …