From a83bf6e8092aea662038f6307517e2970867d676 Mon Sep 17 00:00:00 2001 From: Rachel1809 Date: Mon, 16 Jun 2025 09:37:12 +0700 Subject: [PATCH] Add new paper 'Harry Potter is still here...' which proposed an unlearning evaluation method named LURK to assess the robustness of unlearning algorithm on Harry Potter book --- README.md | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 84e6135..998f972 100644 --- a/README.md +++ b/README.md @@ -34,7 +34,11 @@ As of the last commit, there are **214** papers, **13** surveys and position pap ## Papers ### 2025 - +- [Harry Potter is Still Here! Probing Knowledge Leakage in Targeted Unlearned Large Language Models via Automated Adversarial Prompting](https://arxiv.org/abs/2505.17160) + - Author: Bang Trinh Tran To, Thai Le + - Date: 2025-05 + - Venue: - + - Code: - - [Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs](https://arxiv.org/abs/2505.16831) - Author(s): Xiaoyu Xu, Xiang Yue, Yang Liu, Qingqing Ye, Haibo Hu, Minxin Du - Date: 2025-05