Aluora 1.0.3

Librería para detectar alucinaciones

Aluora

Aluora is a Python library for hallucination detection in text generated by large language models (LLMs). It integrates multiple detection methods to assess the risk that a given response is unsupported or fabricated relative to its context and question.

🔍 Features

• 🧠 HalluDetect: Dropout-based DenseNet model with MC Dropout and mutual information for uncertainty estimation.
• 📐 HHEM: Semantic consistency scoring using a pretrained transformer classifier.
• 🥬 LettuceDetect: Span-level hallucination detection using contextual lexical evaluation.
• 🧪 JSON Output for structured evaluation results.

🚀 Installation

pip install aluora

🧠 Example Usage

from Aluora.core.extractor import hallucination_metrics

hallucination_metrics(
    context="The robot was built in 2023.",
    question="When was the robot built?",
    answer="The robot was built in 2023.",
    output_json_path="results.json"  # path to save output as JSON
)

📁 Output Structure

{
  "halludetect": {
    "predicted_class": 0,
    "label": "🤖 Hallucination",
    "probability_class_1": 0.15,
    "mutual_information": 0.08
  },
  "hhem": {
    "prob_no_hallucination": 0.02,
    "risk_level": "🚨 HIGH"
  },
  "lettuce": {
    "detected_spans": [...],
    "estimated_risk": "⚠️ MEDIUM"
  }
}

📄 License

MIT License

👤 Author

Pedro Sarmiento — GitHub