Memorization in Language Models

Ask about this topic

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

117 papers11 papers in the last four weeks, down 27% on the four weeks before. 0.1% of all new papers.

  1. Self-Keyed In-Parameter Memorization for External Memory-Free Dialogue Recall in Frozen Language Models

    Oct 27, 2026XinYu Piao, Myunghoon Ryu, Joongheon Kim +1Conversational MemoryMemorization in Language Models

    Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea

  2. How Much Information Can We Fit inside a Transformer?

    Oct 25, 2026Amirhossein Basareh, Rishabh Sanjay, Daniel de Mello +1Memorization in Language ModelsTransformer

    Purdue University

  3. ALIAS: Evaluating Performance and Memorization in LLM-Written TLA+ Specifications

    Oct 21, 2026Arslan Bisharat, Mujtaba Nazari, Khushboo Bhadauria +7Memorization in Language ModelsLanguage Model Reasoning Evaluation

    Loyola University Chicago

  4. Benefit and Cost of Random-Token Replacement under Repeated Data: A Known-Entropy Decomposition and Evidence from Ten Real Corpora

    Oct 20, 2026Wonsup Shin, Jingu KimLanguage Model PretrainingData Repetition in Language Model Training

    Flitto

  5. ReproBAIT: Can coding agents build their own biological AI tools?

    Oct 14, 2026Shiv Muthupandiyan, Tolga H. Dur, Mac Walker +8AI Coding AgentsAI Agent Benchmarks

    SecureBio · UK AI Security Institute

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

    Oct 8, 2026Ali Satvaty, Narjes Sharafi, Jirui Qi +2Memorization in Language ModelsPrivacy Leakage in Language Models

    University of Groningen · Leiden University

  7. When Forgetting is not Catastrophic: On the Mechanics of Spurious Forgetting

    Oct 6, 2026Vedant Palit, Florent Draye, Nicolas Zucchet +2Memorization in Language ModelsLLM Fine-Tuning

    MPI for Intelligent Systems, Tübingen · Jinesis Lab, University of Toronto & Vector Institute · EuroSafeAI +3

  8. How Learning Governs Unlearning across the Memorization-Generalization Spectrum

    Oct 6, 2026Hwiyeong Lee, Hyelim Lim, Ingyu Bang +2Memorization in Language ModelsMachine Unlearning

    Seoul National University · Hanyang University · Chung-Ang University

  9. Learning a Fact Is Not Learning How to Retrieve It

    Oct 2, 2026Chaemin Jang, Jihee Kim, Dongman LeeFactual Knowledge in Language ModelsFactual QA

    Korea Advanced Institute of Science and Technology (KAIST)

  10. Late Attention Layers Alone Can Copy Entity Tokens, but Not Without Attending to Their Context

    Sep 28, 2026Muyu He, Yuchen Liu, Ran Tao +1Memorization in Language ModelsLLM Interpretability

    Independent · University of Pennsylvania · Drexel University

  11. MemoReason: Evaluating the Effect of Parametric Memory on Contextual Reasoning in LLMs

    Sep 28, 2026Zineddine Tighidet, Andrea Mogini, Jiali Mei +2LLM EvaluationMemorization in Language Models

    BNP Paribas Paris, France · Sorbonne Université Paris, France · Criteo AI Lab

  12. Don't Forget! Decomposing the Training Dynamics of Memorization in Language Models

    Sep 28, 2026Florian Eichin, Philipp Mondorf, Andrei Mircea +3Memorization in Language ModelsData Repetition in Language Model Training

    MaiNLP, Center for Information and Language Processing, LMU Munich & Munich Center for Machine Learning (MCML), Germany · Mila – Quebec AI Institute & University of Montreal, Canada · Saarland University, Germany

  13. How Linear Attention Remembers

    Sep 27, 2026Kichang Lee, JaeYeon Park, Songkuk Kim +1Linear AttentionMemorization in Language Models

    KAIST · Yonsei University · Dankook University

  14. TRAP: Understanding and Mitigating Privacy Memorization in Language Models

    Sep 26, 2026Muhammed Ustaomeroglu, Ziyue Xu, Hanshen Xiao +3Safety-Preserving Fine-Tuning of Language ModelsMemorization in Language Models

    Carnegie Mellon University · NVIDIA · Purdue University

  15. Generalization and Memorization along the Learning Trajectory of Neural Language Models: A Geometric Account of Categorization

    Sep 26, 2026Wang Bojun, Holly Jenkins, Elizabeth WonnacottMemorization in Language ModelsLanguage Modeling

  16. Memory vs. Context? Influential Factors of Factual Recall in Language Models

    Sep 21, 2026Guilhem Fouilhé, Nicholas Asher, Philippe MullerPrompt SensitivityMemorization in Language Models

    IRIT ANITI · IRIT CNRS · IRIT Université de Toulouse

  17. On the Importance of Gating: Memorization vs. In-Context Learning in State Space Models

    Sep 15, 2026William L. Tong, Aryo Lotfi, Emmanuel Abbe +6Memorization in Language ModelsLong-Context Modeling

    Harvard University · Apple

  18. Specification Oracles

    Sep 11, 2026Atticus Cull, Justin McCarthyMemory-Augmented Language ModelsFactual Knowledge in Language Models

    Diffusion Redwood City, California, USA

  19. The Cost of Compression: A Rate-Distortion Limit on Factual Hallucination

    Sep 10, 2026Xi Wang, Shijia Xu, Rongfeng GuoMemorization in Language ModelsHallucination in Language Models

    Hefei Institutes of Physical Science, Chinese Academy of Sciences, China · University of Science and Technology of China, China · Chongqing University, China +1

  20. Rebalancing Token Importance in Language Models with TF-IDF Weighted Cross-Entropy Loss

    Sep 10, 2026Zhijian Li, Stefan Larson, Kevin LeachMemorization in Language ModelsLLM Fine-Tuning

    University of Southern California, Los Angeles · Vanderbilt University, Nashville

  21. Detectable Only Where It Is Confounded: What Verified Duplication Counts Say About Membership Evidence in Language Models

    Sep 9, 2026Arman Nik KhahMemorization in Language ModelsLLM Auditing

    The University of Texas at Dallas

  22. Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs

    Sep 9, 2026Ravi Ranjan, Olivera Kotevska, Agoritsa PolyzouMemorization in Language ModelsLanguage Model Robustness

    Florida International University (FIU), Miami, FL, USA · Oak Ridge National Laboratory (ORNL), Oak Ridge, TN, USA

  23. From Retrieval to Weights: Parametric Individualization of Small Language Models with Individual Text Corpora

    Sep 9, 2026Christoph Wigbels, Ali Abusaleh, Markus T. Jansen +2Memory-Augmented Language ModelsMemorization in Language Models

    Bergische Universität Wuppertal · Goethe-Universität Frankfurt

  24. Continual Learning Mechanisms Compose for Long-Horizon Memorization

    Sep 7, 2026Zheyuan Zhang, Alvin Zhang, Daniel Khashabi +1Continual Learning for LLMsMemorization in Language Models

    Johns Hopkins University

  25. Exact Record Omission in Delta Attention: A Transport Criterion, Its Cost, and a Replay Certificate

    Sep 6, 2026Vishwajith RameshLLM UnlearningMachine Unlearning Evaluation

    Vy Labs, Inc.

  26. Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization Asymmetry

    Sep 1, 2026Shengfang Zhai, Leo Marchyok, Yuling Shi +4Memorization in Language ModelsMembership Inference Attacks

    National University of Singapore · Oregon State University · Shanghai Jiao Tong University +1

  27. Balancing Privacy, Utility, and Safety in LLM Alignment through Preference Optimization

    Aug 31, 2026Dishu Yang, Jingjing Liu, Jize LiLLM AlignmentMemorization in Language Models

    Khoury College of Computer Sciences Northeastern University San Jose, USA · Department of Electrical Engineering and Computer Sciences University of California, Berkeley Berkeley, USA · Department of Economics Boston University Boston, USA

  28. Where Induction Runs Out: Description-Length Difficulty and the Memorisation Gap in Integer-Sequence Benchmarks

    Aug 29, 2026Sabilashan GaneshanMathematical Reasoning BenchmarksLLM Evaluation

    Independent Researcher

  29. Memorization Is Not Extraction: Tight Differential-Privacy Bounds and Audit Blind Spots

    Aug 27, 2026Xujun Che, Depeng Xu, Shuhan YuanTraining Data ExtractionPrivacy Leakage in Language Models

    University of North Carolina at Charlotte · Utah State University

  30. Beyond Fixed Directions: Adaptive Representation Analysis of Reasoning and Memorization in LLMs

    Aug 22, 2026Shaheen NabiRepresentation Geometry in Language ModelsMemorization in Language Models

    Independent Researcher