Can LLMs Recognize Toxicity? Structured Toxicity Investigation Framework and Semantic-Based Metric

In the pursuit of developing Large Language Models (LLMs) that adhere to societal standards, it is imperative to discern the existence of toxicity in the generated text. The majority of existing toxicity metrics rely on encoder models trained on specific toxicity datasets. However, these encoders are susceptible to out-of-distribution (OOD) problems and depend on the definition of toxicity assumed in a dataset. In this paper, we introduce an automatic robust metric grounded on LLMs to distinguish whether model responses are toxic. We start by analyzing the toxicity factors, followed by examining the intrinsic toxic attributes of LLMs to ascertain their suitability as evaluators. Subsequently, we evaluate our metric, LLMs As ToxiciTy Evaluators (LATTE), on evaluation datasets.The empirical results indicate outstanding performance in measuring toxicity, improving upon state-of-the-art metrics by 12 points in F1 score without training procedure. We also show that upstream toxicity has an influence on downstream metrics.