← Back to all news
arXiv AI By Ali Satvaty, Narjes Sharafi, Jirui Qi, Suzan Verberne, Fatih Turkmen

Is Memorization Context-Sensitive? Prefix-Based Extraction Beyond Isolated Prefixes

Read the original on arXiv AI →

Large language models can reveal memorized training sequences when prompted with a prefix, but real-world systems often use additional context such as instructions or retrieved documents. This study measures how such contextual conditioning affects memorization by comparing suffix probabilities with empty prompts versus retrieved contexts across three instruction-tuned models. The results show that context does not simply erase memorization; instead, it preserves a core set of robustly extractable samples while also shifting the boundary of marginal cases, sometimes suppressing and sometimes enabling new exposures.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Jul 15

Extractable Memorization From First Principles

arXiv:2607. 12649v1 Announce Type: new Abstract: Recent work on extractable memorization in LLMs suffers from two contrasting validity problems.

By A. Feder Cooper, Marika Swanberg, Jamie Hayes, Lea Duesterwald, Christopher De Sa, Daniel E. Ho, Mark A. Lemley, Percy Liang
llms
More like this →
arXiv AI
Oct 1

Mitigating Memorization In Language Models

The paper explores ways to reduce the memorization of training data in language models, testing three regularizer-based, three finetuning-based, and eleven machine unlearning methods—five of which are newly introduced. It introduces TinyMem, a lightweight suite of small models for rapid testing of these mitigation techniques, and shows that unlearning methods, particularly BalancedSubnet, outperform others in removing memorized content while maintaining task performance. The study also finds that regularizer-based approaches are slow and ineffective, while finetuning methods are costly, especially when high accuracy is required.

By Mansi Sakarvadia, Aswathy Ajith, Arham Khan, Nathaniel Hudson, Caleb Geniesse, Kyle Chard, Yaoqing Yang, Ian Foster, Michael W. Mahoney
llmsfine-tuning
More like this →
arXiv Computation and Language
Sep 24

Learning When Not to Listen: Selective Anti-Interference Pretraining for Language Models

The paper introduces Selective Prefix Anti-Interference Regularization (SPAR), a pretraining objective that trains language models to ignore irrelevant distant prefixes. SPAR compares predictions from the original sequence with those from a corrupted prefix that only alters far tokens, using a sufficiency gate and a gated KL loss to stabilize suffix predictions that are already locally supported. Experiments show that SPAR improves robustness metrics such as RULER and NoLiMa across several models, including Qwen2.5, Llama, and GPT2-XL, under equal compute.

By Jinchang Zhu, Haowei He, Yi Ding, Rong Fu, Nie Xiaojian, Shuangyong Song, Zhongjiang He, Menglin Yang
llms
More like this →