AuthorMist Originality is a specialized language model designed to transform AI-generated text into more human-like writing while preserving the original meaning. This model was developed using reinforcement learning techniques to specifically evade AI text detection systems, with a focus on Originality.ai's detection algorithms.
The model is based on Qwen2.5-3B Instruct and has been fine-tuned using Group Relative Policy Optimization (GRPO) with detector feedback as a reward signal. AuthorMist Originality demonstrates strong performance in reducing detectability across multiple AI text detection systems while maintaining high semantic similarity with the original text.
AuthorMist Originality demonstrates exceptional performance in evading AI text detection:
1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3# Load model and tokenizer
4model_name = "authormist/authormist-originality"
5tokenizer = AutoTokenizer.from_pretrained(model_name)
6model = AutoModelForCausalLM.from_pretrained(model_name)
7
8# Prepare input text
9ai_text = "Your AI-generated text here..."
10prompt = f"""Please paraphrase the following text to make it more human-like while preserving the original meaning:
11
12{ai_text}
13
14Paraphrased text:"""
15
16# Generate paraphrased text
17inputs = tokenizer(prompt, return_tensors="pt")
18outputs = model.generate(
19 inputs.input_ids,
20 max_new_tokens=512,
21 temperature=0.7,
22 top_p=0.9,
23 do_sample=True
24)
25paraphrased_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
26print(paraphrased_text.split("Paraphrased text:")[1].strip())
AuthorMist Originality is released for research purposes to advance understanding of AI text detection limitations and privacy-preserving technologies. We acknowledge the dual-use nature of this technology and emphasize the following ethical considerations:
-
Academic Integrity: This model should not be used to misrepresent AI-generated content as human-written in academic settings where such distinctions are ethically relevant.
-
Transparency: We encourage users to maintain transparency about the use of AI assistance in content creation, even when using privacy-enhancing tools like AuthorMist.
-
Privacy Protection: The primary legitimate use case for this technology is protecting author privacy and preventing unfair discrimination against AI-assisted writing in contexts where such assistance is permissible.
-
Research Value: This model provides valuable insights into the limitations of current AI detection systems and contributes to the ongoing research dialogue about AI text detection and privacy.
1@article{authormist2025,
2 title={AuthorMist: Evading AI Text Detectors with Reinforcement Learning},
3 author={David, Isaac and Gervais, Arthur},
4 journal={arXiv preprint},
5 year={2025}
6}
This model is released under the
MIT License.
We thank the developers of Qwen2.5 for the base model and the creators of the CheckGPT dataset for providing valuable training data.
