Search papers, labs, and topics across Lattice.
2
0
4
2
This work investigates how personalization strategies can help improve the effectiveness of answers to questions asked to an LLM-based cybersecurity assistant, and indicates that behavior-driven personalization is a promising direction for LLM-powered cybersecurity assistants.
Matched comparisons reveal that LLMs may reproduce training sequences at alarming rates, but many of these instances are actually false positives rather than true memorization.
