DPP-Based Adversarial Prompt Searching for Lanugage Models

arXiv:2403.00292v1 Announce Type: new
Abstract: Language models risk generating mindless and offensive content, which hinders their safe deployment. Therefore, it is crucial to discover and modify potential toxic outputs of pre-trained language models before deployment. In this work, we elicit toxic content by automatically searching for a prompt that directs pre-trained language models towards the generation of a specific target output. The problem is challenging due to the discrete nature of textual data and the considerable computational resources required for …

abstract adversarial arxiv cs.cl deployment language language models prompt risk searching type work