Automated Humanizer — academic AI-text detector
RoBERTa sequence classifier (human vs. AI-generated) fine-tuned on academic
prose. It is the default hf detector backend of the
automated_humanizer
pipeline, where it gates a humanize → detect → validate rewrite loop.
- Architecture:
RobertaForSequenceClassification, 2 labels - Training data: synthetic (AI-draft, human-original) paragraph pairs
built from award-winning pre-2020 arXiv papers (see the project's
training/subsystem)
Honest limitation
This detector was trained on the same data family as the project's humanizer,
so its confidence is an internal, biased estimate — useful as an
optimization signal inside the loop, not as independent evidence of
authorship. The project README recommends an external detector (e.g. GPTZero)
for final sign-off, and test_detectors.py in the repo reproduces why.
Usage
from transformers import pipeline
clf = pipeline("text-classification", model="avasil02/automated-humanizer-detector")
print(clf("Paragraph of academic text..."))
Check the human-class label index once per deployment with the project's
calibrate_detector.py.
- Downloads last month
- 15