English(EN) Obfuscation Rules for Detecting and Detoxifying Korean Toxicity

新的韩语数据集应对LLM中的混淆毒性语言

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-29 04:00

研究人员推出了KOTOX，一个旨在提高对韩语毒性语言检测和净化能力的新数据集，特别是在用户使用混淆技术时。该数据集对韩语混淆模式进行了分类，并提供了源自真实世界示例的转换规则，从而能够创建成对的中性、毒性和混淆句子。在KOTOX上训练的模型在处理混淆文本方面表现出更强的能力，同时不影响其处理非混淆内容的能力，这标志着在减轻韩语语言模型中伪装的毒性表达方面迈出了重要一步。 AI

影响通过提高对韩语中伪装毒性语言的检测能力，增强了LLM的安全性。

排序理由该集群描述了在arXiv上发布的一篇新学术论文和数据集。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了在arXiv上发布的一篇新学术论文和数据集。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 147 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Yejin Lee, Su-Hyeon Kim, Hyundong Jin, Dayoung Kim, Yeonsoo Kim, Yo-Sub Han · 2026-05-29 04:00

检测和净化韩语毒性内容的混淆规则

arXiv:2510.10961v3 Announce Type: replace-cross Abstract: As language models become increasingly deployed in online environments, toxicity detection and detoxification have received growing attention. Existing studies primarily focus on non-obfuscated text, which limits robustnes…

本文如何被排名

报道来源 [1]

检测和净化韩语毒性内容的混淆规则

相关实体

相关话题