Standard, hierarchical, and weighted conformal prediction applied to LLM watermark scores can control false-positive rates when detecting guideline-violating AI edits in simulated classroom essays.
All experiments were conducted locally using NVIDIA A100-SXM4-40GB GPUs, each with 40GB of VRAM
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.AP 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Watermark in the Classroom: A Conformal Framework for Adaptive AI Usage Detection
Standard, hierarchical, and weighted conformal prediction applied to LLM watermark scores can control false-positive rates when detecting guideline-violating AI edits in simulated classroom essays.