# Measuring Copyright Risks of Large Language Model via Partial Information Probing

arXiv: https://arxiv.org/abs/2409.13831 · HTML: https://mlsanity.com/paper/2409.13831/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 16 references that are in the map.
- First posted on arXiv 20 Sep 2024.

## Builds on (most cited first, 3 of 3)

- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation](https://mlsanity.com/paper/2407.07087/) (2024)

## Built on by (most cited first, 9 of 9)

- [The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage](https://mlsanity.com/paper/2508.09603/) (2025)
- [Context Engineering for Trustworthiness: Rescorla Wagner Steering Under Mixed and Inappropriate Contexts](https://mlsanity.com/paper/2509.04500/) (2025)
- [ISACL: Internal State Analyzer for Copyrighted Training Data Leakage](https://mlsanity.com/paper/2508.17767/) (2025)
- [LogitTrace: Detecting Benchmark Contamination via Layerwise Logit Trajectories](https://mlsanity.com/paper/2509.20909/) (2025)
- [Reflections and New Directions for Human-Centered Large Language Models](https://mlsanity.com/paper/2605.06901/) (2026)
- [Copyright Detective: A Forensic System to Evidence LLMs Flickering Copyright Leakage Risks](https://mlsanity.com/paper/2602.05252/) (2026)
- [Memorization: A Close Look at Books](https://mlsanity.com/paper/2504.12549/) (2025)
- [Copyright Detection in Large Language Models: An Ethical Approach to Generative AI Development](https://mlsanity.com/paper/2511.20623/) (2025)
- [We Should Separate Memorization from Copyright](https://mlsanity.com/paper/2602.08632/) (2026)

## Abstract (arXiv)

Exploring the data sources used to train Large Language Models (LLMs) is a crucial direction in investigating potential copyright infringement by these models. While this approach can identify the possible use of copyrighted materials in training data, it does not directly measure infringing risks. Recent research has shifted towards testing whether LLMs can directly output copyrighted content. Addressing this direction, we investigate and assess LLMs' capacity to generate infringing content by providing them with partial information from copyrighted materials, and try to use iterative prompting to get LLMs to generate more infringing content. Specifically, we input a portion of a copyrighted text into LLMs, prompt them to complete it, and then analyze the overlap between the generated content and the original copyrighted material. Our findings demonstrate that LLMs can indeed generate content highly overlapping with copyrighted materials based on these partial inputs.