# How to Protect Copyright Data in Optimization of Large Language Models?

arXiv: https://arxiv.org/abs/2308.12247 · HTML: https://mlsanity.com/paper/2308.12247/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 65 of its 96 references that are in the map.
- First posted on arXiv 23 Aug 2023.

## Builds on (most cited first, 30 of 65)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [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)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [A Convergence Theory for Deep Learning via Over-Parameterization](https://mlsanity.com/paper/1811.03962/) (2018)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Long Range Arena: A Benchmark for Efficient Transformers](https://mlsanity.com/paper/2011.04006/) (2020)
- [Gradient Descent Provably Optimizes Over-parameterized Neural Networks](https://mlsanity.com/paper/1810.02054/) (2018)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [On Exact Computation with an Infinitely Wide Neural Net](https://mlsanity.com/paper/1904.11955/) (2019)
- [Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks](https://mlsanity.com/paper/1901.08584/) (2019)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [All are Worth Words: A ViT Backbone for Diffusion Models](https://mlsanity.com/paper/2209.12152/) (2022)
- [Fine-Tuning Language Models with Just Forward Passes](https://mlsanity.com/paper/2305.17333/) (2023)
- [Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training](https://mlsanity.com/paper/2305.14342/) (2023)
- [Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data](https://mlsanity.com/paper/1808.01204/) (2018)
- [IntelliCode Compose: Code Generation Using Transformer](https://mlsanity.com/paper/2005.08025/) (2020)
- [AdapterDrop: On the Efficiency of Adapters in Transformers](https://mlsanity.com/paper/2010.11918/) (2020)
- [Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks](https://mlsanity.com/paper/1905.13210/) (2019)
- [Synthesizer: Rethinking Self-Attention in Transformer Models](https://mlsanity.com/paper/2005.00743/) (2020)
- [Towards moderate overparameterization: global convergence guarantees for training shallow neural networks](https://mlsanity.com/paper/1902.04674/) (2019)
- [Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse](https://mlsanity.com/paper/2206.03126/) (2022)
- [Representational Strengths and Limitations of Transformers](https://mlsanity.com/paper/2306.02896/) (2023)

## Built on by (most cited first, 26 of 26)

- [Evaluating Copyright Takedown Methods for Language Models](https://mlsanity.com/paper/2406.18664/) (2024)
- [Copyright Protection in Generative AI: A Technical Perspective](https://mlsanity.com/paper/2402.02333/) (2024)
- [Navigating LLM Ethics: Advancements, Challenges, and Future Directions](https://mlsanity.com/paper/2406.18841/) (2024)
- [An Economic Solution to Copyright Challenges of Generative AI](https://mlsanity.com/paper/2404.13964/) (2024)
- [Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?](https://mlsanity.com/paper/2407.17417/) (2024)
- [GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection](https://mlsanity.com/paper/2505.13312/) (2025)
- [SoK: Dataset Copyright Auditing in Machine Learning Systems](https://mlsanity.com/paper/2410.16618/) (2024)
- [Differential Privacy Mechanisms in Neural Tangent Kernel Regression](https://mlsanity.com/paper/2407.13621/) (2024)
- [Fine-tune Language Models to Approximate Unbiased In-context Learning](https://mlsanity.com/paper/2310.03331/) (2023)
- [Unmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weights](https://mlsanity.com/paper/2310.12462/) (2023)
- [Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens](https://mlsanity.com/paper/2407.21248/) (2024)
- [An Automatic Learning Rate Schedule Algorithm for Achieving Faster Convergence and Steeper Descent](https://mlsanity.com/paper/2310.11291/) (2023)
- [Risks, Causes, and Mitigations of Widespread Deployments of Large Language Models (LLMs): A Survey](https://mlsanity.com/paper/2408.04643/) (2024)
- [The Expressibility of Polynomial based Attention Scheme](https://mlsanity.com/paper/2310.20051/) (2023)
- [A Theoretical Insight into Attack and Defense of Gradient Leakage in Transformer](https://mlsanity.com/paper/2311.13624/) (2023)
- [One Pass Streaming Algorithm for Super Long Token Attention Approximation in Sublinear Space](https://mlsanity.com/paper/2311.14652/) (2023)
- [Tackling Copyright Issues in AI Image Generation Through Originality Estimation and Genericization](https://mlsanity.com/paper/2406.03341/) (2024)
- [Is Your AI Truly Yours? Leveraging Blockchain for Copyrights, Provenance, and Lineage](https://mlsanity.com/paper/2404.06077/) (2024)
- [Strong Copyright Protection for Language Models via Adaptive Model Fusion](https://mlsanity.com/paper/2407.20105/) (2024)
- [Label Smoothing Improves Gradient Ascent in LLM Unlearning](https://mlsanity.com/paper/2510.22376/) (2025)
- [Large Language Models as Search Engines: Societal Challenges](https://mlsanity.com/paper/2512.08946/) (2025)
- [Justifiable Artificial Intelligence: Engineering Large Language Models for Legal Applications](https://mlsanity.com/paper/2311.15716/) (2023)
- [Computational Copyright: Towards A Royalty Model for Music Generative AI](https://mlsanity.com/paper/2312.06646/) (2023)
- [Theoretical Foundation of Flow-Based Time Series Generation: Provable Approximation, Generalization, and Efficiency](https://mlsanity.com/paper/2503.14076/) (2025)
- [Uncertain Boundaries: Multidisciplinary Approaches to Copyright Issues in Generative AI](https://mlsanity.com/paper/2404.08221/) (2024)
- [Enhancing Stochastic Gradient Descent: A Unified Framework and Novel Acceleration Methods for Faster Convergence](https://mlsanity.com/paper/2402.01515/) (2024)

## Abstract (arXiv)

Large language models (LLMs) and generative AI have played a transformative role in computer research and applications. Controversy has arisen as to whether these models output copyrighted data, which can occur if the data the models are trained on is copyrighted. LLMs are built on the transformer neural network architecture, which in turn relies on a mathematical computation called Attention that uses the softmax function. In this paper, we show that large language model training and optimization can be seen as a softmax regression problem. We then establish a method of efficiently performing softmax regression, in a way that prevents the regression function from generating copyright data. This establishes a theoretical method of training large language models in a way that avoids generating copyright data.