Researchers have developed new datasets for the PAN 2026 plagiarism detection task, focusing on identifying original sources of automatically generated text. The study utilized four prominent LLMs: GPT-OSS 120B, Llama 3.1 8B, Qwen 3.5 27B FP8, and DeepSeek-R1 Distill Llama 8B. The task received 26 submissions from six teams, which demonstrated significant improvements over baseline methods. AI
IMPACT This research contributes to the development of tools for detecting AI-generated content, crucial for academic integrity.
RANK_REASON The item is a research paper detailing a task and dataset for plagiarism detection using LLMs. [lever_c_demoted from research: ic=1 ai=1.0]
Read on arXiv cs.IR (Information Retrieval) →
- André Greiner-Petter
- CORE Recommender
- GPT-OSS 120B
- Hugging Face
- Llama-3.1:8b
- PAN 2026
- Qwen 3.5 27B FP8
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →