Ai Text Detector V1.01

🚀 desklib/ai-text-detector-v1.01

這是Desklib開發的一款AI生成文本檢測模型，旨在將英文文本分類為人寫文本或AI生成文本。它目前在RAID AI檢測基準測試中名列前茅。該模型基於Transformer架構，是microsoft/deberta-v3-large的微調版本，具有高精度、魯棒性強的特點，能很好地應對不同領域的各種對抗攻擊。此模型在內容審核、學術誠信、新聞報道等對文本真實性要求較高的場景中非常實用。

Desklib提供基於AI的個性化學習和學習輔助工具，本模型是Desklib為學生、教育工作者和大學提供的眾多工具之一。

在線試用模型！：Desklib AI Detector

Github倉庫：https://github.com/desklib/ai-text-detector

🚀 快速開始

本模型可用於將英文文本分類為人寫文本或AI生成文本，適用於內容審核、學術誠信等場景。你可以通過以下鏈接在線試用模型：Desklib AI Detector ，也可以參考下面的使用示例在本地運行。

✨ 主要特性

• 高精度：在RAID基準測試中表現優異，目前處於領先地位。
• 魯棒性強：能很好地應對不同領域的各種對抗攻擊。
• 應用廣泛：適用於內容審核、學術誠信、新聞報道等對文本真實性要求較高的場景。

📦 安裝指南

文檔未提及具體安裝步驟，可參考以下通用步驟：

1. 確保你已經安裝了Python和transformers庫。
2. 克隆模型的GitHub倉庫：git clone https://github.com/desklib/ai-text-detector.git
3. 進入倉庫目錄並安裝依賴：pip install -r requirements.txt

💻 使用示例

基礎用法

import torch
import torch.nn as nn
from transformers import AutoTokenizer, AutoConfig, AutoModel, PreTrainedModel

class DesklibAIDetectionModel(PreTrainedModel):
    config_class = AutoConfig

    def __init__(self, config):
        super().__init__(config)
        # Initialize the base transformer model.
        self.model = AutoModel.from_config(config)
        # Define a classifier head.
        self.classifier = nn.Linear(config.hidden_size, 1)
        # Initialize weights (handled by PreTrainedModel)
        self.init_weights()

    def forward(self, input_ids, attention_mask=None, labels=None):
        # Forward pass through the transformer
        outputs = self.model(input_ids, attention_mask=attention_mask)
        last_hidden_state = outputs[0]
        # Mean pooling
        input_mask_expanded = attention_mask.unsqueeze(-1).expand(last_hidden_state.size()).float()
        sum_embeddings = torch.sum(last_hidden_state * input_mask_expanded, dim=1)
        sum_mask = torch.clamp(input_mask_expanded.sum(dim=1), min=1e-9)
        pooled_output = sum_embeddings / sum_mask

        # Classifier
        logits = self.classifier(pooled_output)
        loss = None
        if labels is not None:
            loss_fct = nn.BCEWithLogitsLoss()
            loss = loss_fct(logits.view(-1), labels.float())

        output = {"logits": logits}
        if loss is not None:
            output["loss"] = loss
        return output

def predict_single_text(text, model, tokenizer, device, max_len=768, threshold=0.5):
    encoded = tokenizer(
        text,
        padding='max_length',
        truncation=True,
        max_length=max_len,
        return_tensors='pt'
    )
    input_ids = encoded['input_ids'].to(device)
    attention_mask = encoded['attention_mask'].to(device)

    model.eval()
    with torch.no_grad():
        outputs = model(input_ids=input_ids, attention_mask=attention_mask)
        logits = outputs["logits"]
        probability = torch.sigmoid(logits).item()

    label = 1 if probability >= threshold else 0
    return probability, label

def main():
    # --- Model and Tokenizer Directory ---
    model_directory = "desklib/ai-text-detector-v1.01"

    # --- Load tokenizer and model ---
    tokenizer = AutoTokenizer.from_pretrained(model_directory)
    model = DesklibAIDetectionModel.from_pretrained(model_directory)

    # --- Set up device ---
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    model.to(device)

    # --- Example Input text ---
    text_ai = "AI detection refers to the process of identifying whether a given piece of content, such as text, images, or audio, has been generated by artificial intelligence. This is achieved using various machine learning techniques, including perplexity analysis, entropy measurements, linguistic pattern recognition, and neural network classifiers trained on human and AI-generated data. Advanced AI detection tools assess writing style, coherence, and statistical properties to determine the likelihood of AI involvement. These tools are widely used in academia, journalism, and content moderation to ensure originality, prevent misinformation, and maintain ethical standards. As AI-generated content becomes increasingly sophisticated, AI detection methods continue to evolve, integrating deep learning models and ensemble techniques for improved accuracy."
    text_human = "It is estimated that a major part of the content in the internet will be generated by AI / LLMs by 2025. This leads to a lot of misinformation and credibility related issues. That is why if is important to have accurate tools to identify if a content is AI generated or human written"

    # --- Run prediction ---
    probability, predicted_label = predict_single_text(text_ai, model, tokenizer, device)
    print(f"Probability of being AI generated: {probability:.4f}")
    print(f"Predicted label: {'AI Generated' if predicted_label == 1 else 'Not AI Generated'}")

    probability, predicted_label = predict_single_text(text_human, model, tokenizer, device)
    print(f"Probability of being AI generated: {probability:.4f}")
    print(f"Predicted label: {'AI Generated' if predicted_label == 1 else 'Not AI Generated'}")

if __name__ == "__main__":
    main()

📚 詳細文檔

性能表現

該模型在提交時的RAID基準測試中取得了頂尖的成績：訪問RAID排行榜

模型架構

該模型基於微調後的microsoft/deberta-v3-large Transformer架構構建，核心組件包括：

• Transformer基礎模型：預訓練的microsoft/deberta-v3-large模型作為基礎。該模型採用了DeBERTa（具有解耦注意力的解碼增強BERT），它是BERT和RoBERTa的改進版本，結合瞭解耦注意力和增強的掩碼解碼器，以實現更好的性能。
• 均值池化層：該層聚合Transformer的隱藏狀態，創建輸入文本的固定大小表示。此方法通過注意力掩碼對詞元嵌入進行加權平均，以捕捉整體語義。
• 分類器頭：一個線性層作為分類器，接收池化後的表示並輸出單個對數幾率。該對數幾率表示模型對輸入文本是AI生成的置信度。對對數幾率應用Sigmoid激活函數以生成概率。

🔧 技術細節

本模型是基於Transformer架構的文本分類模型，通過微調microsoft/deberta-v3-large模型來實現對英文文本的分類。在模型架構上，採用了均值池化層和線性分類器頭，以提高模型的性能和準確性。同時，模型在訓練過程中使用了RAID基準測試數據集，以確保模型在不同領域和對抗攻擊下的魯棒性。

📄 許可證

本模型採用MIT許可證。