RTP-LX: Can LLMs Evaluate Toxicity in Multilingual Scenarios?

arXiv:2404.14397v1 Announce Type: cross
Abstract: Large language models (LLMs) and small language models (SLMs) are being adopted at remarkable speed, although their safety still remains a serious concern. With the advent of multilingual S/LLMs, the question now becomes a matter of scale: can we expand multilingual safety evaluations of these models with the same velocity at which they are deployed? To this end we introduce RTP-LX, a human-transcreated and human-annotated corpus of toxic prompts and outputs in 28 languages. RTP-LX …

abstract arxiv cs.cl cs.cy cs.lg expand language language models large language large language models llms matter multilingual question safety scale slms small small language models speed toxicity type