ExplainableRecsLM 🚀
ExplainableRecsLM is a recommendation system that not only suggests items to users, but also provides clear, human-readable explanations for every recommendation.
It is designed for transparent AI, trustworthy recommender systems, and explainable AI (XAI) research, and is ready for GitHub, Hugging Face, and Gradio Spaces.
🔍 What Problem Does It Solve?
Traditional recommendation systems act like black boxes.
ExplainableRecsLM answers the critical question:
Why was this item recommended to me?
By combining scoring with natural-language explanations, the system builds user trust and improves interpretability.
✨ Key Features
- 🎯 User–item recommendation engine
- 🧠 Transparent, rule-based scoring
- 🗣️ Human-readable explanations for every recommendation
- 🧩 Modular, extensible design
- 🤗 Hugging Face–ready pipeline
- 🎛️ Gradio web demo included
- 🧪 Test-covered core components
📂 Project Structure
explainable-recs-lm/
├── config/
├── data/
├── src/
├── training/
├── pipelines/
├── scripts/
├── tests/
├── notebooks/
├── app.py
├── README.md
├── model_card.md
├── requirements.txt
└── LICENSE
⚙️ Installation
pip install -r requirements.txt
🚀 Quick Usage
from src.inference import ExplainableRecsPipeline
pipeline = ExplainableRecsPipeline()
results = pipeline(
"data/users.json",
"data/items.json"
)
print(results)
🎛️ Gradio Demo
Run locally:
python app.py
🧠 How It Works
- Feature Extraction
- Scoring
- Ranking
- Explanation Generation
🔮 Future Scope
- ML-based ranking models
- SHAP / attention-based explanations
- Real-time interaction tracking
- Personalized explanation styles
- Domain-specific recommenders
🤗 Hugging Face Details
- Model Name:
explainable-recs-lm - Pipeline Tag:
other - License: Apache-2.0
📜 License
Apache License 2.0
Built for transparent and trustworthy AI recommendations.
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support