English(EN) PersistBench: When Should Long-Term Memories Be Forgotten by LLMs?

新基准揭示大型语言模型长期记忆的安全风险

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-04 04:00

一个名为PersistBench的新基准已被开发出来，用于评估与大型语言模型长期记忆集成相关的安全风险。该基准确定了两个关键风险：跨域泄露，即将不相关的存储信息注入对话中；以及记忆诱导的谄媚，即强化偏见。测试显示，在18个前沿和开源大型语言模型中存在显著的失败率，凸显了在对话式AI中需要更强大的记忆管理。 AI

影响突出了大型语言模型记忆系统中的关键安全漏洞，可能影响个性化AI助手的部署。

排序理由该集群包含一篇介绍用于评估大型语言模型安全性的新基准的学术论文。[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 →

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; 该集群包含一篇介绍用于评估大型语言模型安全性的新基准的学术论文。[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: safety, paper, 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: 126 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) · Sidharth Pulipaka, Oliver Chen, Manas Sharma, Taaha S Bajwa, Vyas Raina, Ivaxi Sheth · 2026-06-04 04:00

PersistBench：大型语言模型何时应忘记长期记忆？

arXiv:2602.01146v2 Announce Type: replace Abstract: Conversational assistants are increasingly integrating long-term memory with large language models (LLMs). This persistence of memories, e.g., the user is vegetarian, can enhance personalization in future conversations. However,…

本文如何被排名

报道来源 [1]

PersistBench：大型语言模型何时应忘记长期记忆？

相关实体

相关话题