You can deploy this model and start earning money today!

Shushant/
adal-paraphraser-large

Name: adal-paraphraser-large
Availability: InStock

Views

No views yet

RADAR Paraphraser (T5-large)

Adversarially trained paraphraser (Gσ) from the RADAR framework (Hu et al., NeurIPS 2023). Trained via Clipped PPO with Entropy Penalty (cppo-ep) to generate paraphrases that evade the companion RADAR detector.

Training

Base model: t5-large
Dataset: RAID
Best detector macro AUROC during adversarial training: 0.9940
Companion detector: Shushant/ADAL-detector-large

Usage

python

from transformers import T5Tokenizer, T5ForConditionalGeneration

tokenizer = T5Tokenizer.from_pretrained("Shushant/adal-paraphraser-large")
model     = T5ForConditionalGeneration.from_pretrained("Shushant/adal-paraphraser-large")

text    = "Paraphrase: " + "Your AI-generated text here."
inputs  = tokenizer(text, return_tensors="pt", truncation=True, max_length=256)
outputs = model.generate(**inputs, max_new_tokens=128, do_sample=True,
                          top_k=50, top_p=0.95)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))