Team xlbn at PAN 2026: Fusion of Multi-domain Features for Generative AI Authorship Verification

Ping-Lun Liu Ai-Guo Wang

· 1 citation · 21 references

TL;DR

An authorship verification method for the PAN 2026 Voight-Kampff Generative AI Detection task that combines word-level TF-IDF, word-boundary character n-gram TF-IDF, and stylometric features to capture complementary textual information.

Semantic Scholar

View source

Similar papers

Pinkey-bw at PAN 2026: Robust Generative AI Authorship Detection using RoBERTa and Stylometric Feature Fusion

Bhavani Savalam, Matti Wiegmann · 1 citation

eGrantha.ai at PAN 2026: Contrastive Representation Learning for Robust Generative AI Authorship Detection Notebook for the PAN Lab at CLEF 2026

Anisha Thapaliya, Shushanta Pudasaini, B. Bal · 0 citations

Team SINAI at PAN 2026: Combining Stylometric Embeddings and IDF Features for Generative AI Text Detection

César Espin-Riofrio, A. Montejo-Ráez, Janis Lara-Jama et al. · 0 citations

2026

Corpus and Baselines for Distinguishing Authentic, AI-Generated, and AI-Enhanced Resumes

A. Loizidou, Anshula Sharma, A. Esquivel et al. · International Conference on... · 0 citations

#large language models Open access Oct 2026

A Lightweight Hybrid Framework for Detecting AI-Generated Scientific Text Using Multi-granularity Features and Language-Model Surprisal

This study presents a lightweight hybrid framework that combines word-level TF–IDF features using 1–3-grams, character-level TF–IDF features using 3–6-grams, calibrated linear classification, and GPT-2-based language-model surprisal through a weighted ensemble to demonstrate the potential of combining multi-granularity...

Pravangkar Boruah · Journal of Scientific Resear... · 0 citations

Team ydong at PAN 2026: Detecting Machine-Generated Text via Multi-Algorithm Compression Distances and Shallow Statistics

Jia-Cai Yang, Qian Dong · 1 citation · ⚡1