PulseAugur
中
实时 22:55:24
English(EN) CBD: API-Only LLM Black-Box Unlearning through Controlled Behavioral Divergence

新的仅API LLM遗忘框架解决了数据移除挑战

研究人员开发了一个名为受控行为分歧(CBD)的新框架,以解决从仅通过API访问的大型语言模型(LLM)中遗忘数据的挑战。CBD使用辅助模型在保留数据和目标数据之间创建分歧,将其转换为遗忘分数,以将不需要的提示从LLM中路由出去。该方法旨在在有效移除敏感或过时信息的同时,保持模型的效用,即使目标数据和保留数据具有相似的结构。 AI

影响 这项研究可以实现更有效和注重隐私的更新LLM的方法,而无需完全重新训练,尤其是在仅API的场景下。

排序理由 该集群包含一篇详细介绍LLM中机器学习遗忘新方法的学术论文。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新的仅API LLM遗忘框架解决了数据移除挑战

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
Research
该集群包含一篇详细介绍LLM中机器学习遗忘新方法的学术论文。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
100 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 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Zhiqiang Xie, Yijing Lin, Zhipeng Gao, Dong In Kim ·

    CBD:通过受控行为差异实现仅API的大语言模型黑盒遗忘

    arXiv:2606.27683v1 Announce Type: cross Abstract: Edge devices increasingly invoke large language models (LLMs) through API services for context aware edge intelligence, while edge generated data may be collected to improve LLMs and may introduce sensitive, copyrighted, harmful, …

  2. arXiv cs.LG TIER_1 English(EN) · Dong In Kim ·

    CBD:通过受控行为分歧实现仅API的LLM黑箱遗忘

    Edge devices increasingly invoke large language models (LLMs) through API services for context aware edge intelligence, while edge generated data may be collected to improve LLMs and may introduce sensitive, copyrighted, harmful, or outdated information into model behavior. Machi…