ICML 2025 Workshop MemFM Submissions

Language models’ activations linearly encode training-order recency
Dmitrii Krasheninnikov, Richard E. Turner, David Krueger
- Published: 11 Jun 2025, Last Modified: 13 Jul 2025
- MemFM
- Readers: Everyone
Localizing and Mitigating Memorization in Image Autoregressive Models
Aditya Kasliwal, Franziska Boenisch, Adam Dziedzic
- Published: 11 Jun 2025, Last Modified: 13 Jul 2025
- MemFM
- Readers: Everyone
Mitigating Unintended Memorization with LoRA in Federated Learning for LLMs
Thierry Bossy, Julien Tuấn Tú Vignoud, Tahseen Rabbani, Juan R. Troncoso Pastoriza, Martin Jaggi
- Published: 11 Jun 2025, Last Modified: 13 Jul 2025
- MemFM
- Readers: Everyone
ContextLeak: Auditing Leakage in Private In-Context Learning Methods
Jacob Choi, Shuying Cao, Xingjian Dong, Sai Praneeth Karimireddy
- Published: 11 Jun 2025, Last Modified: 14 Jul 2025
- MemFM
- Readers: Everyone
Are Samples Extracted From Large Language Models Memorized?
Chawin Sitawarin, Karan Chadha, John Xavier Morris, Saeed Mahloujifar, Chuan Guo
- Published: 11 Jun 2025, Last Modified: 13 Jul 2025
- MemFM
- Readers: Everyone
Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs
Qinyuan Wu, Soumi Das, Mahsa Amani, Bishwamittra Ghosh, Mohammad Aflah Khan, Krishna P. Gummadi, Muhammad Bilal Zafar
- Published: 11 Jun 2025, Last Modified: 14 Jul 2025
- MemFM
- Readers: Everyone
How Can I Publish My LLM Benchmark Without Giving the True Answers Away?
Takashi Ishida, Thanawat Lodkaew, Ikko Yamane
- Published: 11 Jun 2025, Last Modified: 13 Jul 2025
- MemFM
- Readers: Everyone
Personal Information Parroting in Language Models
Nishant Subramani, Kshitish Ghate, Mona T. Diab
- Published: 11 Jun 2025, Last Modified: 13 Jul 2025
- MemFM
- Readers: Everyone
OWL: Probing Cross-Lingual Recall of Memorized Texts via World Literature
Alisha Srivastava, Emir Kaan Korukluoglu, Minh Nhat Le, Duyen Tran, Chau Minh Pham, Marzena Karpinska, Mohit Iyyer
- Published: 11 Jun 2025, Last Modified: 14 Jul 2025
- MemFM
- Readers: Everyone
Low-Rank Adaptation Secretly Imitates Differentially Private SGD
Saber Malekmohammadi, Golnoosh Farnadi
- Published: 11 Jun 2025, Last Modified: 14 Jul 2025
- MemFM
- Readers: Everyone
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data
Tong Chen, Faeze Brahman, Jiacheng Liu, Niloofar Mireshghallah, Weijia Shi, Pang Wei Koh, Luke Zettlemoyer, Hannaneh Hajishirzi
- Published: 11 Jun 2025, Last Modified: 13 Jul 2025
- MemFM
- Readers: Everyone
A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective
Lianghe Shi, Meng Wu, Huijie Zhang, Zekai Zhang, Molei Tao, Qing Qu
- Published: 11 Jun 2025, Last Modified: 13 Jul 2025
- MemFM
- Readers: Everyone
OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics
Vineeth Dorna, Anmol Mekala, Wenlong Zhao, Andrew McCallum, J Zico Kolter, Zachary Chase Lipton, Pratyush Maini
- Published: 11 Jun 2025, Last Modified: 13 Jul 2025
- MemFM
- Readers: Everyone
MAGIC: Diffusion Model Memorization Auditing via Generative Image Compression
Gunjan Dhanuka, Sumukh K Aithal, Avi Schwarzschild, Zhili Feng, J Zico Kolter, Zachary Chase Lipton, Pratyush Maini
- Published: 11 Jun 2025, Last Modified: 14 Jul 2025
- MemFM
- Readers: Everyone
Rethinking Memorization Measures in LLMs: Recollection vs. Counterfactual vs. Contextual Memorization
Bishwamittra Ghosh, Soumi Das, Qinyuan Wu, Mohammad Aflah Khan, Krishna P. Gummadi, Evimaria Terzi, Deepak Garg
- Published: 11 Jun 2025, Last Modified: 13 Jul 2025
- MemFM
- Readers: Everyone
Trade-offs in Data Memorization via Strong Data Processing Inequalities
Vitaly Feldman, Guy Kornowski, Xin Lyu
- Published: 11 Jun 2025, Last Modified: 13 Jul 2025
- MemFM
- Readers: Everyone
Bigger Isn’t Always Memorizing: Early Stopping Overparameterized Diffusion Models
Alessandro Favero, Antonio Sclocchi, Matthieu Wyart
- Published: 11 Jun 2025, Last Modified: 13 Jul 2025
- MemFM
- Readers: Everyone
Counterfactual Influence as a Distributional Quantity
Matthieu Meeus, Igor Shilov, Georgios Kaissis, Yves-Alexandre de Montjoye
- Published: 11 Jun 2025, Last Modified: 13 Jul 2025
- MemFM
- Readers: Everyone
An Empirical Exploration of Continual Unlearning for Image Generation
Justin Lee, Zheda Mai, Chongyu Fan, Wei-Lun Chao
- Published: 11 Jun 2025, Last Modified: 13 Jul 2025
- MemFM
- Readers: Everyone
Early-stopping Too Late? Traces of Memorization Before Overfitting in Generative Diffusion
Jerome Garnier-Brun, Luca Biggio, Marc Mezard, Luca Saglietti
- Published: 11 Jun 2025, Last Modified: 13 Jul 2025
- MemFM
- Readers: Everyone
GenAI Copyright Evidence with Operational Meaning
Eli Chien, Amit Saha, Yinan Huang, Pan Li
- Published: 11 Jun 2025, Last Modified: 13 Jul 2025
- MemFM
- Readers: Everyone
Evaluating Memorization in Parameter-Efficient Fine-tuning
Sanghyun Hong, Nicholas Carlini, Alexey Kurakin
- Published: 11 Jun 2025, Last Modified: 13 Jul 2025
- MemFM
- Readers: Everyone
Knowledge‑Distilled Memory Editing for Plug‑and‑Play LLM Alignment
Haozheng Luo, Jiahao Yu, Wenxin Zhang, Jialong Li, Jerry Yao-Chieh Hu, Yan Chen, Binghui Wang, Xinyu Xing, Han Liu
- Published: 11 Jun 2025, Last Modified: 13 Jul 2025
- MemFM
- Readers: Everyone
Low Resource Reconstruction Attacks Through Benign Prompts
Sol Yarkoni, Roi Livni
- Published: 11 Jun 2025, Last Modified: 13 Jul 2025
- MemFM
- Readers: Everyone
Mirage of Mastery: Memorization Tricks LLMs into Artificially Inflated Self-Knowledge
Sahil Kale
- Published: 11 Jun 2025, Last Modified: 13 Jul 2025
- MemFM
- Readers: Everyone