Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models

arXiv:2401.10647v2 Announce Type: replace
Abstract: In the rapidly advancing field of artificial intelligence, the concept of Red-Teaming or Jailbreaking large language models (LLMs) has emerged as a crucial area of study. This approach is especially significant in terms of assessing and enhancing the safety and robustness of these models. This paper investigates the intricate consequences of such modifications through model editing, uncovering a complex relationship between enhancing model accuracy and preserving its ethical integrity. Our in-depth analysis reveals a striking …

abstract artificial artificial intelligence arxiv concept cs.cl editing impact intelligence jailbreaking language language models large language large language models llms robustness safety study terms type wind