PulseAugur
中
实时 13:10:19
English(EN) Reversible Pseudonymisation of Documents Sent to External LLMs: an Open Bilingual Benchmark and an Engine

新引擎和基准改进了用于大语言模型的文档假名化

一篇新研究论文介绍了一个开放的基准和引擎,用于对发送至外部大语言模型的文档进行可逆假名化。该基准在俄语和英国英语数据集上评估了五个现有工具和一个新引擎,测试它们用占位符替换个人数据并在响应中准确恢复数据的能力。虽然现有工具未能达到标识符和泄露检测的预定阈值,但新引擎的准确率显著提高,几乎没有可见数据泄露,并在英国英语中恢复了超过99%的占位符,尽管由于屈折变化,它在俄语姓名恢复方面遇到了一些挑战。 AI

影响 增强了与外部大语言模型交互的用户的数据隐私,可能增加敏感文档处理的采用率。

排序理由 详细介绍文档假名化新基准和引擎的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

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

新引擎和基准改进了用于大语言模型的文档假名化

本文如何被排名

Signal score
8 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
详细介绍文档假名化新基准和引擎的研究论文。[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
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.CL TIER_1 English(EN) · Vladimir Beskorovainyi ·

    发送至外部LLM文档的可逆假名化:一个开放的双语基准和引擎

    arXiv:2610.34012v1 Announce Type: new Abstract: Professionals send working documents to external large language models. A common safeguard is reversible pseudonymisation: personal data are replaced with placeholders before the request and restored locally in the answer. We presen…