---
id: 20260313-T0-10
title: "arXiv论文提出LLM可解释遗忘方法"
title_en: "arXiv Paper Proposes Explainable LLM Unlearning Method"
url: https://ai.daily.yangsir.net/daily/20260313-T0-10
issue_date: 2026-03-13
publish_date: 2026-03-12T04:00:00.000Z
source_name: "arXiv cs.LG (ML)"
source_url: https://arxiv.org/abs/2603.09980
---

# arXiv论文提出LLM可解释遗忘方法

arXiv论文2603.09980v1提出基于推理的大模型可解释遗忘方法，通过安全消除特定知识来解决版权、隐私等风险。相比偏好对齐，该方法提供更明确的知识移除机制，适用于敏感数据清理场景。

## English Version

**arXiv Paper Proposes Explainable LLM Unlearning Method**

arXiv paper 2603.09980v1 introduces an explainable LLM unlearning method based on reasoning, enabling safe removal of specific knowledge to address copyright, privacy and safety concerns. Unlike preference alignment, this method provides explicit knowledge removal mechanisms.

---

**来源**：[arXiv cs.LG (ML)](https://arxiv.org/abs/2603.09980)

**详情页**：https://ai.daily.yangsir.net/daily/20260313-T0-10

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*