按年被提到
20242024 · 1 次2026
大模型与语言模型›大模型预训练与缩放·arXiv:2410.16454 · cs.CL

Catastrophic Failure of LLM Unlearning via Quantization

Zhiwei Zhang, Fali Wang, Xiaomin Li, Zongyu Wu, Xianfeng Tang, Hui Liu, Qi He, Wenpeng Yin, Suhang Wang · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2024-11-04 · 最近 2025-10-09
2不同的人
2活跃月份
2讨论串
12被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Large language models (LLMs) have shown remarkable proficiency in generating text, benefiting from extensive training on vast textual corpora. However, LLMs may also acquire unwanted behaviors from the diverse and sensitive nature of their training data, which can include copyrighted and private content. Machine unlearning has been introduced as a viable solution to remove the influence of such problematic content without the need for costly and time-consuming retraining. This process aims to erase specific knowledge from LLMs while preserving as much model utility as possible. Despite the effectiveness of current unlearning methods, little attention has been given to whether existing unlearning methods for LLMs truly achieve forgetting or merely hide the knowledge, which current unlearning benchmarks fail to detect. This paper reveals that applying quantization to models that have undergone unlearning can restore the "forgotten" information. To thoroughly evaluate this phenomenon, we conduct comprehensive experiments using various quantization techniques across multiple precision levels. We find that for unlearning methods with utility constraints, the unlearned model retains an average of 21\% of the intended forgotten knowledge in full precision, which significantly increases to 83\% after 4-bit quantization. ... Our code is available at: \href{https://github.com/zzwjames/FailureLLMUnlearning}{https://github.com/zzwjames/FailureLLMUnlearning}.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论sigbottle · 2025-10

“Not necessarily? The way these models are trained suggests "more good data is more good". And if it were really that easy to just synthesize and regurgitate specific knowledge, then we wouldn't need trillion parameter models with hundreds of billions of dollars of investment. A key thing in classical ML training too is to not overfit an anomaly; you real…”

A small number of samples can poison LLMs of any size原评论 ↗
被提交为 story · 1 次