PulseAugur
中
实时 10:16:35
English(EN) ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models

新的基准测试ReasoningShield改进了大型语言模型推理轨迹的安全检测

作者 PulseAugur 编辑部 · [1 个来源] ·

研究人员开发了ReasoningShield，这是一个新的基准测试和模型套件，旨在改进大型推理模型（LRMs）中推理轨迹的安全检测。现有的审核工具难以处理思维链（CoT）推理，表现出显著的性能下降。ReasoningShield通过提供一个包含9.2K个带注释的CoT对的数据集和轻量级模型来解决这个问题，这些模型达到了91.8%的F1分数，优于LlamaGuard-4和GPT-4o等当前领先的工具。 AI

影响 通过改进对中间推理步骤中有害内容的检测，增强了大型语言模型的安全协议。

排序理由 该集群描述了一篇介绍用于人工智能安全研究的新基准测试和模型的新学术论文。[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 →

新的基准测试ReasoningShield改进了大型语言模型推理轨迹的安全检测

本文如何被排名

Signal score
11 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群描述了一篇介绍用于人工智能安全研究的新基准测试和模型的新学术论文。[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, model release
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
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Changyi Li, Jiayi Wang, Xudong Pan, Geng Hong, Min Yang ·

    ReasoningShield：大型推理模型推理轨迹上的安全检测

    arXiv:2505.17244v3 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) leverage explicit reasoning traces, known as Chain-of-Thought (CoT) reasoning, to decompose complex problems into intermediate steps before deriving final answers. However, these reasoning tra…

相关实体

相关话题