Skip to content
Python

Update README.md

SNOW TEAMb258a1b03af6
diff --git a/README.md b/README.md
index 57a27fa..74eed21 100644
--- a/README.md
+++ b/README.md
@@ -18,20 +18,57 @@ Qi Chen, [Siria Xiyueyao Luo](https://www.rug.nl/staff/x.luo/?lang=en), [Xuejiao
[![Stargazers repo roster for @SNOWTEAM2023/GEM](https://reporoster.com/stars/SNOWTEAM2023/GEM)](https://github.com/SNOWTEAM2023/GEM/stargazers)
+## :fire: News
+* **[2026.02.01]** We release github repository of **Cognivia**. πŸ’ͺ Have a try!
-## Overview
+## 🧭 Framework Overview
<p align="center">
<img src="https://github.com/SNOWTEAM2023/Cognivia/blob/main/overview.jpg" width="400">
</p>
+**GEM** aligns base LLM using human preference data by a **Coginitive Feedback Loop**, which includes **Cognitive Filtering** and **SEGA** modules.
+Key modules of GEM include:
+
+- **Cognitive Filtering**: Generate `k` Chain-of-Thought (CoTs) candidates per query and **rank** them by Entropy-guided Token Scoring module. Entropy-guided Token Scoring module encourages **exploration mid‑CoT** (high entropy on top‑m steps) and **confidence at the end** (low final entropy).
+- **SEGA**: A **listwise** objective that updates the policy using **group-mean–centered advantages**, which update with weights proportional to **Aα΅’ = rα΅’ βˆ’ rΜ„** within each k-way group.
## Dataset
+1. **CBT Cognitive Triplet Dataset**:
+2. **Augmented CBT Cognitive Triplet Dataset**:
+
+
+### ✨ Code Structure
+The code structure and corresponding comments of this repository are as follows:
+
+```
+GEM/
+β”œβ”€β”€ GEM.py # Main entry script for running GEM
+β”œβ”€β”€ data/ # Example preference data
+β”‚ └── preference_data.jsonl
+β”‚
+β”œβ”€β”€ src/ # Core implementation of GEM
+β”‚ β”œβ”€β”€ __init__.py
+β”‚ β”œβ”€β”€ config.py # Configuration utilities
+β”‚ β”œβ”€β”€ dataset.py # Dataset & dataloader definitions
+β”‚ β”œβ”€β”€ entropy_scorer.py # Entropy-based scoring
+β”‚ β”œβ”€β”€ gem_trainer.py # GEM training pipeline
+β”‚ └── sft_trainer.py # Supervised fine-tuning (SFT) trainer
+β”‚
+β”œβ”€β”€ materials/ # Figures & assets for the paper
+β”œβ”€β”€ README.md # Project introduction and usage
+β”œβ”€β”€ LICENCE.txt # Licence information
+└── requirements.txt # Python dependencies
+```
+
## Usage
## Experiments
# Main results
## Evaluation
+## πŸ”‘ License
+This work is licensed under the [Creative Commons Attribution-NonCommercial 4.0 International License](http://creativecommons.org/licenses/by-nc/4.0/).
+Commercial use is prohibited without a separate license agreement with the author.