跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.20443 · v1

Overview of the Plagiarism Detection Task at PAN 2026

首次提交 2026-11-16 11:14
版本更新 2026-11-16 11:14
雷达观测 2026-11-17 13:07
arXiv ↗PDF ↗

摘要

The generative plagiarism detection task at PAN 2026 aims at retrieving the original scientific sources for given automatically generated textual plagiarism. We created two novel datasets of synthetically generated plagiarism following the premise of a malicious actor trying to generate papers with minimal effort while evading detection of undisclosed re-use. We utilized four widely available LLMs: GPT-OSS 120B, Llama 3.1 8B, Qwen 3.5 27B FP8, and DeepSeek-R1 Distill Llama 8B. In this task overview paper, we outline the creation of this dataset and summarize and compare the results of all participants with three baselines. For this year's task, we received 26 submissions from six teams that significantly outperformed our baselines.

作者备注:Corrected version of the paper published in CEUR-WS Vol-4283: an error in the one-shot generation dataset was fixed and the one-shot results (Sec. 2.3, Table 3, Figs. 2, 3, 6) were updated; the sequential dataset and its results are unchanged. DOI: 10.5281/zenodo.23528623 (Version v3)

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-16 11:14 · 最新观测版本

Overview of the Plagiarism Detection Task at PAN 2026

The generative plagiarism detection task at PAN 2026 aims at retrieving the original scientific sources for given automatically generated textual plagiarism. We created two novel datasets of synthetically generated plagiarism following the premise of a malicious actor trying to generate papers with minimal effort while evading detection of undisclosed re-use. We utilized four widely available LLMs: GPT-OSS 120B, Llama 3.1 8B, Qwen 3.5 27B FP8, and DeepSeek-R1 Distill Llama 8B. In this task overview paper, we outline the creation of this dataset and summarize and compare the results of all participants with three baselines. For this year's task, we received 26 submissions from six teams that significantly outperformed our baselines.

查看此版本解读 →查看此版本原文 ↗