Text Classification
Transformers
Safetensors
English
distilbert
ai-text-detection
academic-integrity
paperguard
text-embeddings-inference

PaperGuard AI Detector (v2.0)

Fine-tuned DistilBERT (distilbert-base-cased) sequence classifier that detects AI-generated text in academic papers, essays, and reports. It is the core AI-detection engine of the PaperGuard multi-agent academic-integrity system.

Labels

0 = ai, 1 = human (see config.json id2label).

Training data

v2.0 ("mega") continues from the v1.5 checkpoint and adds a larger, more diverse mix so the model sees many modern LLM writing styles:

  • Claude Opus distillation β€” recent Anthropic-style generations
  • Ateeqq/AI-and-Human-Generated-Text β€” academic abstracts (human + AI)
  • artem9k/ai-text-detection-pile β€” large open human-vs-AI corpus
  • (v1.5 lineage) Defactify + Ateeqq, spanning 30+ frontier LLMs (GPT-4o, LLaMA-3, Claude 3, Gemini, Mistral, Qwen, ChatGPT, …)

Important: use the logit margin, not the raw softmax

On easy/separable data the model becomes overconfident β€” its softmax saturates (it can report 0% AI even on genuine AI text). The discriminative signal lives in the logit margin (human_logit βˆ’ ai_logit). PaperGuard therefore scores AI-likelihood from a logistic calibration of the margin, not the raw softmax. After calibration it flags clean/academic AI at ~70–90% while keeping human text low (10%).

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

tok = AutoTokenizer.from_pretrained("vediumsameer/paperguard-ai-detector")
model = AutoModelForSequenceClassification.from_pretrained("vediumsameer/paperguard-ai-detector")

text = "The rapid advancement of artificial intelligence has transformed modern education..."
inputs = tok(text, return_tensors="pt", truncation=True, max_length=512)
with torch.no_grad():
    logits = model(**inputs).logits[0]

# Recommended: score off the margin (softmax is saturated)
margin = float(logits[model.config.label2id["human"]] - logits[model.config.label2id["ai"]])
# lower margin  -> more AI-like ; higher margin -> more human-like
print("logit margin (human - ai):", margin)

Limitations

  • Blind spot: slang / style-masked AI (an LLM told to write casually) can still read as human. PaperGuard mitigates this with embedding-based stylometric "patchwork" detection, and a v2.1 trained on adversarial / multi-model / reasoning data is planned to close the gap.
  • AI detection is a probabilistic indicator, not proof of authorship.

Part of PaperGuard

This model powers the AI-detection layer of PaperGuard, which also does citation claim verification, plagiarism, and writing-quality analysis. See the project repo.

Downloads last month
18
Safetensors
Model size
65.8M params
Tensor type
F32
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Datasets used to train vediumsameer/paperguard-ai-detector