# Source Attribution for Large Language Model-Generated Data

arXiv: https://arxiv.org/abs/2310.00646 · HTML: https://mlsanity.com/paper/2310.00646/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Privacy-preserving tabular data synthesis, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 22 of its 43 references that are in the map.
- First posted on arXiv 1 Oct 2023.

## Placed in

- Synthetic data and self-improvement for LLMs / [Privacy-preserving tabular data synthesis](https://mlsanity.com/synth/privacy-preserving-tabular-data-synthesis/)
- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

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

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers](https://mlsanity.com/paper/1801.04354/) (2018)
- [Robust Distortion-free Watermarks for Language Models](https://mlsanity.com/paper/2307.15593/) (2023)
- [Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data](https://mlsanity.com/paper/2007.08457/) (2020)
- [Do GANs leave artificial fingerprints?](https://mlsanity.com/paper/1812.11842/) (2018)
- [BookSum: A Collection of Datasets for Long-form Narrative Summarization](https://mlsanity.com/paper/2105.08209/) (2021)
- [Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding](https://mlsanity.com/paper/2009.03015/) (2020)
- [On the Use of ArXiv as a Dataset](https://mlsanity.com/paper/1905.00075/) (2019)
- [Protecting Intellectual Property of Language Generation APIs with Lexical Watermark](https://mlsanity.com/paper/2112.02701/) (2021)
- [Neural Linguistic Steganography](https://mlsanity.com/paper/1909.01496/) (2019)
- [A Large Self-Annotated Corpus for Sarcasm](https://mlsanity.com/paper/1704.05579/) (2017)
- [Watermarking Pre-trained Language Models with Backdooring](https://mlsanity.com/paper/2210.07543/) (2022)
- [Distillation-Resistant Watermarking for Model Protection in NLP](https://mlsanity.com/paper/2210.03312/) (2022)
- [Watermarking Text Data on Large Language Models for Dataset Copyright](https://mlsanity.com/paper/2305.13257/) (2023)
- [DeepHider: A Covert NLP Watermarking Framework Based on Multi-task Learning](https://mlsanity.com/paper/2208.04676/) (2022)

## Built on by (most cited first, 11 of 11)

- [A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://mlsanity.com/paper/2312.02003/) (2023)
- [Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Era](https://mlsanity.com/paper/2404.11457/) (2024)
- [Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions](https://mlsanity.com/paper/2406.04606/) (2024)
- [Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration](https://mlsanity.com/paper/2410.01285/) (2024)
- [Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Models](https://mlsanity.com/paper/2508.15396/) (2025)
- [Memorization in In-Context Learning](https://mlsanity.com/paper/2408.11546/) (2024)
- [Large Language Model Sourcing: A Survey](https://mlsanity.com/paper/2510.10161/) (2025)
- [TRACE: TRansformer-based Attribution using Contrastive Embeddings in LLMs](https://mlsanity.com/paper/2407.04981/) (2024)
- [Invariant Features in Language Models: Geometric Characterization and Model Attribution](https://mlsanity.com/paper/2605.06458/) (2026)
- [Sovereign Context Protocol: An Open Attribution Layer for Human-Generated Content in the Age of Large Language Models](https://mlsanity.com/paper/2603.27094/) (2026)
- [FindMyText: Robust, Scalable Detection of Text Containment in Large Web-Crawled Corpora](https://mlsanity.com/paper/2607.10020/) (2026)

## Abstract (arXiv)

The impressive performances of Large Language Models (LLMs) and their immense potential for commercialization have given rise to serious concerns over the Intellectual Property (IP) of their training data. In particular, the synthetic texts generated by LLMs may infringe the IP of the data being used to train the LLMs. To this end, it is imperative to be able to perform source attribution by identifying the data provider who contributed to the generation of a synthetic text by an LLM. In this paper, we show that this problem can be tackled by watermarking, i.e., by enabling an LLM to generate synthetic texts with embedded watermarks that contain information about their source(s). We identify the key properties of such watermarking frameworks (e.g., source attribution accuracy, robustness against adversaries), and propose a source attribution framework that satisfies these key properties due to our algorithmic designs. Our framework enables an LLM to learn an accurate mapping from the generated texts to data providers, which sets the foundation for effective source attribution. Extensive empirical evaluations show that our framework achieves effective source attribution.