paper-with-me

홈 › Papers

Localizing Paragraph Memorization in Language Models

2024-03-28 · Niklas Stoehr, Mitchell Gordon, Chiyuan Zhang, Owen Lewis

Can we localize the weights and mechanisms used by a language model to memorize and recite entire paragraphs of its training data? In this paper, we show that while memorization is spread across multiple layers and model components, gradients of memorized paragraphs have a distinguishable spatial pattern, being larger in lower model layers than gradients of non-memorized examples. Moreover, the memorized examples can be unlearned by fine-tuning only the high-gradient weights. We localize a low-layer attention head that appears to be especially involved in paragraph memorization. This head is predominantly focusing its attention on distinctive, rare tokens that are least frequent in a corpus-level unigram distribution. Next, we study how localized memorization is across the tokens in the prefix by perturbing tokens and measuring the caused change in the decoding. A few distinctive tokens early in a prefix can often corrupt the entire continuation. Overall, memorized continuations are not only harder to unlearn, but also to corrupt than non-memorized ones.

📄 PDF Abstract BibTeX arXiv:2403.19851

Code (1)

googleinterns/localizing-paragraph-memorization 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingMemorization

Similar Papers 제목 키워드 기반

Localizing Memorization in SSL Vision Encoders

2024-09-27 · Wenhao Wang, Adam Dziedzic, Michael Backes, Franziska Boenisch

Recent work on studying memorization in self-supervised learning (SSL) suggests that even though SSL encoders are trained on millions of images, they still memorize individual data points. While effort has been put into …

MemorizationSelf-Supervised Learning

Siamese Learning with Joint Alignment and Regression for Weakly-Supervised Video Paragraph Grounding

2024-03-18 · CVPR 2024 1 · Chaolei Tan, JianHuang Lai, Wei-Shi Zheng, Jian-Fang Hu

Video Paragraph Grounding (VPG) is an emerging task in video-language understanding, which aims at localizing multiple sentences with semantic relations and temporal order from an untrimmed video. However, existing VPG a…

Multiple Instance Learning

Localizing and Mitigating Memorization in Image Autoregressive Models

2025-08-30 · Aditya Kasliwal, Franziska Boenisch, Adam Dziedzic arxiv

Image AutoRegressive (IAR) models have achieved state-of-the-art performance in speed and quality of generated images. However, they also raise concerns about memorization of their training data and its implications for …

Localizing Memorized Regions in Diffusion Models via Coordinate-Wise Curvature Differences

2026-05-26 · Gwangho Kim, Sungyoon Lee arxiv

Diffusion models can unintentionally memorize training samples, raising concerns about privacy and copyright. While recent methods can detect memorization, they often rely on global or model-specific signals and provide …

Dense Object Grounding in 3D Scenes

2023-09-05 · Wencan Huang, Daizong Liu, Wei Hu

Localizing objects in 3D scenes according to the semantics of a given natural language is a fundamental yet important task in the field of multimedia understanding, which benefits various real-world applications such as …

Autonomous DrivingDecoderObjectSentence