# Do Language Models Plagiarize?

arXiv: https://arxiv.org/abs/2203.07618 · HTML: https://mlsanity.com/paper/2203.07618/

## Key facts

- Cited by 73 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 97 references that are in the map.
- First posted on arXiv 15 Mar 2022.

## Builds on (most cited first, 30 of 43)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [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)
- [Deduplicating Training Data Mitigates Privacy Risks in Language Models](https://mlsanity.com/paper/2202.06539/) (2022)
- [All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text](https://mlsanity.com/paper/2107.00061/) (2021)
- [Automatic Detection of Generated Text is Easiest when Humans are Fooled](https://mlsanity.com/paper/1911.00650/) (2019)
- [What Does it Mean for a Language Model to Preserve Privacy?](https://mlsanity.com/paper/2202.05520/) (2022)
- [CORD-19: The COVID-19 Open Research Dataset](https://mlsanity.com/paper/2004.10706/) (2020)
- [Facebook FAIR's WMT19 News Translation Task Submission](https://mlsanity.com/paper/1907.06616/) (2019)
- [Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference](https://mlsanity.com/paper/1906.11798/) (2019)
- [Counterfactual Memorization in Neural Language Models](https://mlsanity.com/paper/2112.12938/) (2021)
- [How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN](https://mlsanity.com/paper/2111.09509/) (2021)
- [Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning](https://mlsanity.com/paper/1904.01067/) (2019)
- [TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation](https://mlsanity.com/paper/2109.13296/) (2021)
- [Trading Off Diversity and Quality in Natural Language Generation](https://mlsanity.com/paper/2004.10450/) (2020)
- [Toxicity Detection: Does Context Really Matter?](https://mlsanity.com/paper/2006.00998/) (2020)
- [Analyzing Information Leakage of Updates to Natural Language Models](https://mlsanity.com/paper/1912.07942/) (2019)
- [Ethical Challenges in Data-Driven Dialogue Systems](https://mlsanity.com/paper/1711.09050/) (2017)
- [Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information](https://mlsanity.com/paper/2010.03142/) (2020)
- [Leveraging BERT for Extractive Text Summarization on Lectures](https://mlsanity.com/paper/1906.04165/) (2019)
- [A Non-Parametric Test to Detect Data-Copying in Generative Models](https://mlsanity.com/paper/2004.05675/) (2020)
- [Patent Claim Generation by Fine-Tuning OpenAI GPT-2](https://mlsanity.com/paper/1907.02052/) (2019)

## Built on by (most cited first, 30 of 73)

- [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (2023)
- [Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature](https://mlsanity.com/paper/2310.05130/) (2023)
- [Analyzing Leakage of Personally Identifiable Information in Language Models](https://mlsanity.com/paper/2302.00539/) (2023)
- [Understanding and Mitigating Copying in Diffusion Models](https://mlsanity.com/paper/2305.20086/) (2023)
- [Foundation Models and Fair Use](https://mlsanity.com/paper/2303.15715/) (2023)
- [Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset](https://mlsanity.com/paper/2207.00220/) (2022)
- [A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions](https://mlsanity.com/paper/2310.14724/) (2023)
- [On Provable Copyright Protection for Generative Models](https://mlsanity.com/paper/2302.10870/) (2023)
- [Language Model Behavior: A Comprehensive Survey](https://mlsanity.com/paper/2303.11504/) (2023)
- [Trustworthiness in Retrieval-Augmented Generation Systems: A Survey](https://mlsanity.com/paper/2409.10102/) (2024)
- [A Design Space for Intelligent and Interactive Writing Assistants](https://mlsanity.com/paper/2403.14117/) (2024)
- [Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems](https://mlsanity.com/paper/2401.05778/) (2024)
- [On the Societal Impact of Open Foundation Models](https://mlsanity.com/paper/2403.07918/) (2024)
- [SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)](https://mlsanity.com/paper/2406.17975/) (2024)
- [Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs](https://mlsanity.com/paper/2406.10209/) (2024)
- [Training Data Extraction From Pre-trained Language Models: A Survey](https://mlsanity.com/paper/2305.16157/) (2023)
- [Exploring Memorization in Fine-tuned Language Models](https://mlsanity.com/paper/2310.06714/) (2023)
- [GPT-who: An Information Density-based Machine-Generated Text Detector](https://mlsanity.com/paper/2310.06202/) (2023)
- [Copyright Protection in Generative AI: A Technical Perspective](https://mlsanity.com/paper/2402.02333/) (2024)
- [SoK: Memorization in General-Purpose Large Language Models](https://mlsanity.com/paper/2310.18362/) (2023)
- [Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models](https://mlsanity.com/paper/2502.18943/) (2025)
- [Undesirable Memorization in Large Language Models: A Survey](https://mlsanity.com/paper/2410.02650/) (2024)
- [Adaptive Ensembles of Fine-Tuned Transformers for LLM-Generated Text Detection](https://mlsanity.com/paper/2403.13335/) (2024)
- [Does Human Collaboration Enhance the Accuracy of Identifying LLM-Generated Deepfake Texts?](https://mlsanity.com/paper/2304.01002/) (2023)
- [AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees](https://mlsanity.com/paper/2510.01268/) (2025)
- [An Evaluation on Large Language Model Outputs: Discourse and Memorization](https://mlsanity.com/paper/2304.08637/) (2023)
- [Citation: A Key to Building Responsible and Accountable Large Language Models](https://mlsanity.com/paper/2307.02185/) (2023)
- [Causal Estimation of Memorisation Profiles](https://mlsanity.com/paper/2406.04327/) (2024)
- [Reward Reports for Reinforcement Learning](https://mlsanity.com/paper/2204.10817/) (2022)
- [Noise-Robust De-Duplication at Scale](https://mlsanity.com/paper/2210.04261/) (2022)

## Abstract (arXiv)

Past literature has illustrated that language models (LMs) often memorize parts of training instances and reproduce them in natural language generation (NLG) processes. However, it is unclear to what extent LMs "reuse" a training corpus. For instance, models can generate paraphrased sentences that are contextually similar to training samples. In this work, therefore, we study three types of plagiarism (i.e., verbatim, paraphrase, and idea) among GPT-2 generated texts, in comparison to its training data, and further analyze the plagiarism patterns of fine-tuned LMs with domain-specific corpora which are extensively used in practice. Our results suggest that (1) three types of plagiarism widely exist in LMs beyond memorization, (2) both size and decoding methods of LMs are strongly associated with the degrees of plagiarism they exhibit, and (3) fine-tuned LMs' plagiarism patterns vary based on their corpus similarity and homogeneity. Given that a majority of LMs' training data is scraped from the Web without informing content owners, their reiteration of words, phrases, and even core ideas from training sets into generated texts has ethical implications. Their patterns are likely to exacerbate as both the size of LMs and their training data increase, raising concerns about indiscriminately pursuing larger models with larger training corpora. Plagiarized content can also contain individuals' personal and sensitive information. These findings overall cast doubt on the practicality of current LMs in mission-critical writing tasks and urge more discussions around the observed phenomena. Data and source code are available at https://github.com/Brit7777/LM-plagiarism.