# Overview of the Plagiarism Detection Task at PAN 2025

arXiv: https://arxiv.org/abs/2510.06805 · HTML: https://mlsanity.com/paper/2510.06805/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 8 Oct 2025.

## Builds on (most cited first, 8 of 8)

- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [The Science of Detecting LLM-Generated Texts](https://mlsanity.com/paper/2303.07205/) (2023)
- [A Theoretical Analysis of the Repetition Problem in Text Generation](https://mlsanity.com/paper/2012.14660/) (2020)
- [ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness](https://mlsanity.com/paper/2305.12947/) (2023)
- [How Large Language Models are Transforming Machine-Paraphrased Plagiarism](https://mlsanity.com/paper/2210.03568/) (2022)
- [Linq-Embed-Mistral Technical Report](https://mlsanity.com/paper/2412.03223/) (2024)
- [Are Neural Language Models Good Plagiarists? A Benchmark for Neural Paraphrase Detection](https://mlsanity.com/paper/2103.12450/) (2021)

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

- [SciFigPlag-Bench: A Benchmark for Provenance-Aware Scientific Figure Plagiarism Detection](https://mlsanity.com/paper/2607.29124/) (2026)
- [Beyond Representational Similarity: Source-Conditioned Description-Length Gain for Generative Plagiarism Detection and Candidate Source Reranking](https://mlsanity.com/paper/2608.03859/) (2026)

## Abstract (arXiv)

The generative plagiarism detection task at PAN 2025 aims at identifying automatically generated textual plagiarism in scientific articles and aligning them with their respective sources. We created a novel large-scale dataset of automatically generated plagiarism using three large language models: Llama, DeepSeek-R1, and Mistral. In this task overview paper, we outline the creation of this dataset, summarize and compare the results of all participants and four baselines, and evaluate the results on the last plagiarism detection task from PAN 2015 in order to interpret the robustness of the proposed approaches. We found that the current iteration does not invite a large variety of approaches as naive semantic similarity approaches based on embedding vectors provide promising results of up to 0.8 recall and 0.5 precision. In contrast, most of these approaches underperform significantly on the 2015 dataset, indicating a lack in generalizability.