Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models

arxiv(2022)

引用 17|浏览88
暂无评分
摘要
Large language models produce human-like text that drive a growing number of applications. However, recent literature and, increasingly, real world observations, have demonstrated that these models can generate language that is toxic, biased, untruthful or otherwise harmful. Though work to evaluate language model harms is under way, translating foresight about which harms may arise into rigorous benchmarks is not straightforward. To facilitate this translation, we outline six ways of characterizing harmful text which merit explicit consideration when designing new benchmarks. We then use these characteristics as a lens to identify trends and gaps in existing benchmarks. Finally, we apply them in a case study of the Perspective API, a toxicity classifier that is widely used in harm benchmarks. Our characteristics provide one piece of the bridge that translates between foresight and effective evaluation.
更多
查看译文
关键词
harmful text,rigorous benchmarking,language
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要