# Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon

arXiv: https://arxiv.org/abs/2406.17746 · HTML: https://mlsanity.com/paper/2406.17746/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 38 references that are in the map.
- First posted on arXiv 25 Jun 2024.

## Builds on (most cited first, 26 of 26)

- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [Deduplicating Training Data Makes Language Models Better](https://mlsanity.com/paper/2107.06499/) (2021)
- [Benign Overfitting in Linear Regression](https://mlsanity.com/paper/1906.11300/) (2019)
- [Beyond neural scaling laws: beating power law scaling via data pruning](https://mlsanity.com/paper/2206.14486/) (2022)
- [Does Learning Require Memorization? A Short Tale about a Long Tail](https://mlsanity.com/paper/1906.05271/) (2019)
- [Detecting Pretraining Data from Large Language Models](https://mlsanity.com/paper/2310.16789/) (2023)
- [Deduplicating Training Data Mitigates Privacy Risks in Language Models](https://mlsanity.com/paper/2202.06539/) (2022)
- [What Does it Mean for a Language Model to Preserve Privacy?](https://mlsanity.com/paper/2202.05520/) (2022)
- [Counterfactual Memorization in Neural Language Models](https://mlsanity.com/paper/2112.12938/) (2021)
- [Emergent and Predictable Memorization in Large Language Models](https://mlsanity.com/paper/2304.11158/) (2023)
- [The Privacy Onion Effect: Memorization is Relative](https://mlsanity.com/paper/2206.10469/) (2022)
- [Copyright Violations and Large Language Models](https://mlsanity.com/paper/2310.13771/) (2023)
- [Rethinking LLM Memorization through the Lens of Adversarial Compression](https://mlsanity.com/paper/2404.15146/) (2024)
- [Copyright Traps for Large Language Models](https://mlsanity.com/paper/2402.09363/) (2024)
- [Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting](https://mlsanity.com/paper/2207.06569/) (2022)
- [Defending against Reconstruction Attacks with R'enyi Differential Privacy](https://mlsanity.com/paper/2202.07623/) (2022)
- [Unveiling Memorization in Code Models](https://mlsanity.com/paper/2308.09932/) (2023)
- [Provably Confidential Language Modelling](https://mlsanity.com/paper/2205.01863/) (2022)
- [Measures of Information Reflect Memorization Patterns](https://mlsanity.com/paper/2210.09404/) (2022)
- [Memorisation Cartography: Mapping out the Memorisation-Generalisation Continuum in Neural Machine Translation](https://mlsanity.com/paper/2311.05379/) (2023)

## Built on by (most cited first, 30 of 31)

- [On Memorization of Large Language Models in Logical Reasoning](https://mlsanity.com/paper/2410.23123/) (2024)
- [Demystifying Verbatim Memorization in Large Language Models](https://mlsanity.com/paper/2407.17817/) (2024)
- [Knowledge Mechanisms in Large Language Models: A Survey and Perspective](https://mlsanity.com/paper/2407.15017/) (2024)
- [Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics](https://mlsanity.com/paper/2505.00675/) (2025)
- [CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation](https://mlsanity.com/paper/2407.07087/) (2024)
- [Undesirable Memorization in Large Language Models: A Survey](https://mlsanity.com/paper/2410.02650/) (2024)
- [VaultGemma: A Differentially Private Gemma Model](https://mlsanity.com/paper/2510.15001/) (2025)
- [Analyzing Memorization in Large Language Models through the Lens of Model Attribution](https://mlsanity.com/paper/2501.05078/) (2025)
- [Beyond Math: Stories as a Testbed for Memorization-Constrained Reasoning in LLMs](https://mlsanity.com/paper/2412.14368/) (2024)
- [Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training](https://mlsanity.com/paper/2502.15680/) (2025)
- [Extracting alignment data in open models](https://mlsanity.com/paper/2510.18554/) (2025)
- [Composable Interventions for Language Models](https://mlsanity.com/paper/2407.06483/) (2024)
- [OWL: Probing Cross-Lingual Recall of Memorized Texts via World Literature](https://mlsanity.com/paper/2505.22945/) (2025)
- [Empirical Privacy Variance](https://mlsanity.com/paper/2503.12314/) (2025)
- [KScope: A Framework for Characterizing the Knowledge Status of Language Models](https://mlsanity.com/paper/2506.07458/) (2025)
- [Position: Don't Just "Fix it in Post": A Science of AI Must Study Training Dynamics](https://mlsanity.com/paper/2606.06533/) (2026)
- [MemHunter: Automated and Verifiable Memorization Detection at Dataset-scale in LLMs](https://mlsanity.com/paper/2412.07261/) (2024)
- [Memorization Inheritance in Sequence-Level Knowledge Distillation for Neural Machine Translation](https://mlsanity.com/paper/2502.01491/) (2025)
- [Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack](https://mlsanity.com/paper/2506.02711/) (2025)
- [Mirage of Mastery: Memorization Tricks LLMs into Artificially Inflated Self-Knowledge](https://mlsanity.com/paper/2506.18998/) (2025)
- [A Prior-Aware Metric for Efficiently Distinguishing Memorization from Generalization in Large Language Models](https://mlsanity.com/paper/2602.18733/) (2026)
- [Erase Persona, Forget Lore: Benchmarking Multimodal Copyright Unlearning in Large Vision Language Models](https://mlsanity.com/paper/2605.03547/) (2026)
- [Low-Perplexity LLM-Generated Sequences and Where To Find Them](https://mlsanity.com/paper/2507.01844/) (2025)
- [Data Compressibility Quantifies LLM Memorization](https://mlsanity.com/paper/2507.06056/) (2025)
- [Diffusion Models Preferentially Memorize Prototypical Examples or: Why Does My Diffusion Model Love Slop?](https://mlsanity.com/paper/2605.30642/) (2026)
- [Exposing Assumptions in AI Benchmarks through Cognitive Modelling](https://mlsanity.com/paper/2409.16849/) (2024)
- [Beyond Frequency: The Role of Redundancy in Large Language Model Memorization](https://mlsanity.com/paper/2506.12321/) (2025)
- [Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data](https://mlsanity.com/paper/2606.16952/) (2026)
- [Enhancing SLMs for Sustainable Code Optimization in Radio-Astronomy](https://mlsanity.com/paper/2607.21677/) (2026)
- [Generalization and Memorization along the Learning Trajectory of Neural Language Models: A Geometric Account of Categorization](https://mlsanity.com/paper/2609.32199/) (2026)

## Abstract (arXiv)

Memorization in language models is typically treated as a homogenous phenomenon, neglecting the specifics of the memorized data. We instead model memorization as the effect of a set of complex factors that describe each sample and relate it to the model and corpus. To build intuition around these factors, we break memorization down into a taxonomy: recitation of highly duplicated sequences, reconstruction of inherently predictable sequences, and recollection of sequences that are neither. We demonstrate the usefulness of our taxonomy by using it to construct a predictive model for memorization. By analyzing dependencies and inspecting the weights of the predictive model, we find that different factors influence the likelihood of memorization differently depending on the taxonomic category.