Hubble: a Model Suite to Advance the Study of LLM Memorization
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918165803433984 |
|---|---|
| author | Wei, Johnny Tian-Zheng Godbole, Ameya Khan, Mohammad Aflah Wang, Ryan Zhu, Xiaoyuan Flemings, James Kashyap, Nitya Gummadi, Krishna P. Neiswanger, Willie Jia, Robin |
| author_facet | Wei, Johnny Tian-Zheng Godbole, Ameya Khan, Mohammad Aflah Wang, Ryan Zhu, Xiaoyuan Flemings, James Kashyap, Nitya Gummadi, Krishna P. Neiswanger, Willie Jia, Robin |
| contents | We present Hubble, a suite of fully open-source large language models (LLMs) for the scientific study of LLM memorization. Hubble models come in standard and perturbed variants: standard models are pretrained on a large English corpus, and perturbed models are trained in the same way but with controlled insertion of text (e.g., book passages, biographies, and test sets) designed to emulate key memorization risks. Our core release includes 8 models -- standard and perturbed models with 1B or 8B parameters, pretrained on 100B or 500B tokens -- establishing that memorization risks are determined by the frequency of sensitive data relative to size of the training corpus (i.e., a password appearing once in a smaller corpus is memorized better than the same password in a larger corpus). Our release also includes 6 perturbed models with text inserted at different pretraining phases, showing that sensitive data without continued exposure can be forgotten. These findings suggest two best practices for addressing memorization risks: to dilute sensitive data by increasing the size of the training corpus, and to order sensitive data to appear earlier in training. Beyond these general empirical findings, Hubble enables a broad range of memorization research; for example, analyzing the biographies reveals how readily different types of private information are memorized. We also demonstrate that the randomized insertions in Hubble make it an ideal testbed for membership inference and machine unlearning, and invite the community to further explore, benchmark, and build upon our work. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_19811 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hubble: a Model Suite to Advance the Study of LLM Memorization Wei, Johnny Tian-Zheng Godbole, Ameya Khan, Mohammad Aflah Wang, Ryan Zhu, Xiaoyuan Flemings, James Kashyap, Nitya Gummadi, Krishna P. Neiswanger, Willie Jia, Robin Computation and Language Machine Learning We present Hubble, a suite of fully open-source large language models (LLMs) for the scientific study of LLM memorization. Hubble models come in standard and perturbed variants: standard models are pretrained on a large English corpus, and perturbed models are trained in the same way but with controlled insertion of text (e.g., book passages, biographies, and test sets) designed to emulate key memorization risks. Our core release includes 8 models -- standard and perturbed models with 1B or 8B parameters, pretrained on 100B or 500B tokens -- establishing that memorization risks are determined by the frequency of sensitive data relative to size of the training corpus (i.e., a password appearing once in a smaller corpus is memorized better than the same password in a larger corpus). Our release also includes 6 perturbed models with text inserted at different pretraining phases, showing that sensitive data without continued exposure can be forgotten. These findings suggest two best practices for addressing memorization risks: to dilute sensitive data by increasing the size of the training corpus, and to order sensitive data to appear earlier in training. Beyond these general empirical findings, Hubble enables a broad range of memorization research; for example, analyzing the biographies reveals how readily different types of private information are memorized. We also demonstrate that the randomized insertions in Hubble make it an ideal testbed for membership inference and machine unlearning, and invite the community to further explore, benchmark, and build upon our work. |
| title | Hubble: a Model Suite to Advance the Study of LLM Memorization |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2510.19811 |