Shushant/adal-roberta-detector

RADAR Detector (RoBERTa-large)

Adversarially trained AI-generated text detector based on the RADAR framework (Hu et al., NeurIPS 2023), extended with a multi-evasion attack pool for robust detection.

Training

• Base model: roberta-large
• Dataset: RAID (Dugan et al., ACL 2024)
• Evasion attacks seen during training: t5_paraphrase, synonym_replacement, homoglyphs, article_deletion, misspelling
• Best macro AUROC: 0.6897
• Generators: chatgpt, gpt2, gpt3, gpt4, cohere, cohere-chat, llama-chat, mistral, mistral-chat, mpt, mpt-chat

Usage

from transformers import RobertaTokenizer, RobertaForSequenceClassification
import torch

tokenizer = RobertaTokenizer.from_pretrained("Shushant/adal-roberta-detector")
model     = RobertaForSequenceClassification.from_pretrained("Shushant/adal-roberta-detector")
model.eval()

text = "Your text here."
enc  = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)
with torch.no_grad():
    probs = torch.softmax(model(**enc).logits, dim=-1)[0]
print(f"P(human)={probs[1]:.3f}  P(AI)={probs[0]:.3f}")

Label mapping

• Index 0 → AI-generated
• Index 1 → Human-written