PolygloToxicityPrompts：大型语言模型神经毒性退化的多语言评估
PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models
AI总结：
本文提出首个覆盖17种语言、包含425K条提示的多语言毒性评估基准PTP，通过对60多个LLMs的评测发现毒性随语言资源减少和模型规模增大而上升，并揭示了现有安全调优方法的局限。
摘要：
大型语言模型（LLMs）的最新进展促使其在全球范围内广泛部署，确保其安全性需要全面且多语言的毒性评估。然而，现有的毒性基准测试绝大多数集中在英语上，这给在其他语言中部署LLMs带来了严重风险。我们通过引入PolygloToxicityPrompts（PTP）来解决这一问题，这是首个大规模多语言毒性评估基准，包含覆盖17种语言的425K条自然出现的提示。我们通过自动抓取超过1亿份网络文本文档，克服了网络文本中自然出现毒性样本的稀缺问题，并确保在不同资源水平的语言中实现覆盖。利用PTP，我们研究了模型规模、提示语言以及指令调优和偏好调优方法对毒性的影响，并对超过60个LLMs进行了基准测试。值得注意的是，我们发现随着语言资源的减少或模型规模的增大，毒性会上升。尽管指令调优和偏好调优能够降低毒性，但偏好调优方法的选择并没有显著影响。我们的研究结果揭示了LLM安全防护的关键缺陷，并指出了未来研究的方向。
英文摘要：
Recent advances in large language models (LLMs) have led to their extensive global deployment, and ensuring their safety calls for comprehensive and multilingual toxicity evaluations. However, existing toxicity benchmarks are overwhelmingly focused on English, posing serious risks to deploying LLMs in other languages. We address this by introducing PolygloToxicityPrompts (PTP), the first large-scale multilingual toxicity evaluation benchmark of 425K naturally occurring prompts spanning 17 languages. We overcome the scarcity of naturally occurring toxicity in web-text and ensure coverage across languages with varying resources by automatically scraping over 100M web-text documents. Using PTP, we investigate research questions to study the impact of model size, prompt language, and instruction and preference-tuning methods on toxicity by benchmarking over 60 LLMs. Notably, we find that toxicity increases as language resources decrease or model size increases. Although instruction- and preference-tuning reduce toxicity, the choice of preference-tuning method does not have any significant impact. Our findings shed light on crucial shortcomings of LLM safeguarding and highlight areas for future research.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
