English(EN) Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges

新的中文安全基准 C-SafeQA 评估大型语言模型响应和评判者

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-02 04:00

研究人员开发了 C-SafeQA，一个用于评估大型语言模型响应安全性的新基准，尤其是在中文方面。该基准侧重于识别不安全响应，而不仅仅是风险查询，解决了语言变异和对抗性攻击带来的挑战。C-SafeQA 包括基础查询和对抗性查询，由人类专家和七个自动化安全评判者评估响应，揭示了评判者性能的显著权衡以及在对抗某些转换时的特定弱点。 AI

影响提供了一个评估和改进大型语言模型安全性的新工具，尤其是在处理细微的中文内容方面。

排序理由该集群包含一篇详细介绍大型语言模型安全评估新基准的研究论文。[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: 32 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍大型语言模型安全评估新基准的研究论文。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Rui Yang, Shuang Huang, Junhua Liu, Ziqi Zhao, Qingzhong Yan, Yuhang Sun, Cong Liu, Guoping Hu, Rui Mei, Jing Shao · 2026-09-02 04:00

谁来评判评判者？一个用于评估大型语言模型响应和安全评判者的中文安全问答基准

arXiv:2609.01210v1 Announce Type: cross Abstract: Safety benchmarks for large language models often assess the risk of a user query, although the outcome of question answering depends on whether the response violates a policy. This distinction is critical in Chinese harmful-conte…

本文如何被排名

报道来源 [1]

谁来评判评判者？一个用于评估大型语言模型响应和安全评判者的中文安全问答基准

相关实体

相关话题