Memorization in Language Models

Overview

Researchers study when models reproduce training text or personal data, retain factual knowledge, and generalize beyond examples—questions that matter for privacy, benchmark validity, and reliable use. Common approaches include canary and text-extraction attacks, membership inference, matched training and non-training comparisons, and mechanistic analysis of activations and training dynamics; evaluations include privacy audits and unlearning benchmarks such as TOFU and MUSE. Mitigations range from data filtering and training-objective changes to fine-tuning, unlearning, and targeted edits to model activations or parameters, while agent-memory benchmarks test long-horizon recall. A central tension is that storing information does not guarantee it will be revealed, and reducing leakage must preserve useful recall and generalization.

Latest papers

CardsList

126 papers12 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

  1. Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs

    Jan 16, 2026Lecheng Yan, Ruizhe Li, Guanhua Chen +5Reward HackingMemorization in Language Models

  2. MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewards

    Jan 9, 2026Zhiyu Shen, Ziming Wu, Fuming Lai +2Reinforcement LearningMemory-Augmented Language Models

  3. Understanding the Interplay between Memorization and Learning in Large Language Models

    Jul 20, 2025Bishwamittra Ghosh, Soumi Das, Qinyuan Wu +4Memorization in Language ModelsLLM Training

  4. Evaluating Harmful Memorization in LLM Code Generation

    Mar 4, 2025Lizhe Zhang, Wentao Chen, Li Zhong +3Memorization in Language ModelsLLM Code Generation

  5. Continual Memorization of Factoids in Language Models

    Nov 11, 2024Howard Chen, Jiayi Geng, Adithya Bhaskar +2Continual Learning for LLMsMemorization in Language Models

  6. Mitigating Memorization In Language Models

    Oct 3, 2024Mansi Sakarvadia, Aswathy Ajith, Arham Khan +6Memorization in Language ModelsLLM Fine-Tuning