Realistic Evaluation of Toxicity in Large Language Models

arXiv:2405.10659v1 Announce Type: new
Abstract: Large language models (LLMs) have become integral to our professional workflows and daily lives. Nevertheless, these machine companions of ours have a critical flaw: the huge amount of data which endows them with vast and diverse knowledge, also exposes them to the inevitable toxicity and bias. While most LLMs incorporate defense mechanisms to prevent the generation of harmful content, these safeguards can be easily bypassed with minimal prompt engineering. In this paper, we introduce the …

abstract arxiv become bias cs.ai cs.cl daily data diverse evaluation integral knowledge language language models large language large language models llms machine professional them toxicity type vast while workflows