SEED integrates similarity-guided data augmentation, a DINOv3-based ViT with LoRA for joint detection and localization, and an evolving MLLM harness to generate explainable forensic reports, placing 3rd in the GenText-Forensics Challenge.
2026.๐ NNProxy: Efficient Training-Free Proxy Alignment for Black-Box Zero-Shot LLM-Generated Text Detection.arXiv preprint arXiv:2604.02008(2026)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SEED: Simple ViT and Evolving Harness for Explainable Text Forgery Detection
SEED integrates similarity-guided data augmentation, a DINOv3-based ViT with LoRA for joint detection and localization, and an evolving MLLM harness to generate explainable forensic reports, placing 3rd in the GenText-Forensics Challenge.