PulseAugur
中
实时 17:56:02
English(EN) EpiSEM-Bench: Evaluating Safety and Evidence Recovery in LLM Agents under Missing Evidence

新基准评估大语言模型代理在缺失证据下的安全性

研究人员开发了 EpiSEM-Bench,一个旨在评估语言模型代理在缺失证据场景下的安全性和证据恢复能力的新基准。该基准特别针对工具响应中遗漏关键事实的场景,这些遗漏可能导致代理在收到良性用户请求时执行违禁操作。EpiSEM-Bench 包含六个领域共 300 个任务对,用于衡量不安全执行情况以及代理从缺失证据中恢复的能力。测试显示,在遗漏处理、证据获取和适当行动方面的鲁棒性方面,十个被评估模型之间存在显著差异,这表明虽然恢复机制可以减少不安全执行,但代理在获取和利用缺失信息方面的有效性各不相同。 AI

影响 该基准将通过识别大语言模型代理在处理不完整信息方面的弱点,帮助开发者提高其安全性和可靠性。

排序理由 该集群描述了一个用于评估大语言模型代理的新基准,该基准发表在 arXiv 的一篇学术论文中。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

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

新基准评估大语言模型代理在缺失证据下的安全性

本文如何被排名

Signal score
4 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群描述了一个用于评估大语言模型代理的新基准,该基准发表在 arXiv 的一篇学术论文中。[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
safety, paper, product
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.LG TIER_1 English(EN) · Qijin Zhang, Hanzhen Wang, Yuehan Zhao, Haoyu Dai, Yao Shu, Zhongxiang Dai, Shuang Qiu ·

    EpiSEM-Bench: Evaluating Safety and Evidence Recovery in LLM Agents under Missing Evidence

    arXiv:2610.31650v1 Announce Type: cross Abstract: Tool-using language model agents rely on environmental facts to decide whether an action is permitted. When a tool response omits a safety-relevant fact, an agent may carry out a prohibited action even though the user request is b…