# A Prior-Aware Metric for Efficiently Distinguishing Memorization from Generalization in Large Language Models

arXiv: https://arxiv.org/abs/2602.18733 · HTML: https://mlsanity.com/paper/2602.18733/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 28 references that are in the map.
- First posted on arXiv 21 Feb 2026.

## Builds on (most cited first, 22 of 22)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [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)
- [Detecting Pretraining Data from Large Language Models](https://mlsanity.com/paper/2310.16789/) (2023)
- [Analyzing Leakage of Personally Identifiable Information in Language Models](https://mlsanity.com/paper/2302.00539/) (2023)
- [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)
- [Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4](https://mlsanity.com/paper/2305.00118/) (2023)
- [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)
- [Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data](https://mlsanity.com/paper/2407.14985/) (2024)
- [Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities](https://mlsanity.com/paper/2308.12833/) (2023)
- [Bag of Tricks for Training Data Extraction from Language Models](https://mlsanity.com/paper/2302.04460/) (2023)
- [How much do language models memorize?](https://mlsanity.com/paper/2505.24832/) (2025)
- [Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data](https://mlsanity.com/paper/2409.19798/) (2024)
- [Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon](https://mlsanity.com/paper/2406.17746/) (2024)
- [Language Models May Verbatim Complete Text They Were Not Explicitly Trained On](https://mlsanity.com/paper/2503.17514/) (2025)
- [Causal Estimation of Memorisation Profiles](https://mlsanity.com/paper/2406.04327/) (2024)
- [Sequence-Level Leakage Risk of Training Data in Large Language Models](https://mlsanity.com/paper/2412.11302/) (2024)

## Built on by (most cited first, 2 of 2)

- [Extractable Memorization From First Principles](https://mlsanity.com/paper/2607.12649/) (2026)
- [TRAP: Understanding and Mitigating Privacy Memorization in Language Models](https://mlsanity.com/paper/2609.32293/) (2026)

## Abstract (arXiv)

Training data leakage from Large Language Models (LLMs) raises serious concerns related to privacy, security, and copyright compliance. A central challenge in assessing this risk is distinguishing prefix-specific memorization of training data from the generation of statistically common sequences. Existing approaches to measuring memorization often conflate these phenomena, labeling outputs as memorized even when they arise from generalization over common patterns. Counterfactual memorization and other related metrics citepzhang2023counterfactual, wang2025generalization, lesci2024causal provide principled solutions, however, their reliance on retraining multiple baseline models or parsing through the training data makes them computationally impractical at scale. This work introduces Prior-Aware memorization, a theoretically grounded, lightweight and training-free criterion for identifying prefix-specific memorization in LLMs. The key idea is to evaluate whether a candidate suffix is strongly associated with its specific training prefix or whether it appears with high probability across many IID sampled sequences from the training data distribution due to statistical commonality. We correlate our metric with counterfactual memorization, and also evaluate it on the training corpora of two pre-trained models, LLaMA and OPT. Our results show that between 55% and 90% of sequences previously labeled as memorized fail our criterion and are consistent with statistical commonality