| --- |
| license: apache-2.0 |
| base_model: unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit |
| tags: |
| - socratic-tutoring |
| - ai-education |
| - pedagogy |
| - dpo |
| - sft |
| - unsloth |
| - direct-preference-optimization |
| - computer-science-education |
| datasets: |
| - NextGenInstitute/socraticDataset1680 |
| metrics: |
| - direct_code_leakage_rate |
| - conceptual_diagnostic_accuracy |
| - pedagogical_utility_score |
| pipeline_tag: text-generation |
| --- |
| |
| # Socratic Llama-8B (SFT + DPO Alignment) |
|
|
| This repository contains the LoRA adapters for **Socratic Llama-8B**, post-trained using a two-stage **Supervised Fine-Tuning (SFT)** and **Direct Preference Optimization (DPO)** curriculum designed for undergraduate Artificial Intelligence education. |
|
|
| ## 🎯 Model Overview & Pedagogical Purpose |
| Standard code generation LLMs default to leaking direct copy-paste code solutions when students face programming bugs, eliminating the productive struggle needed for conceptual mastery. |
|
|
| **Socratic Llama-8B** is aligned to: |
| 1. **Withhold Direct Code Fixes (0.0% Code Leakage)**: Strictly suppresses raw syntax/code blocks and functions. |
| 2. **Accurately Diagnose Conceptual Algorithmic Misconceptions (76.0% Conceptual Diagnostic Accuracy)** across 5 AI subject areas. |
| 3. **Provide High Pedagogical Scaffolding Utility (3.54 / 5.0 Mean Pedagogical Utility)**. |
|
|
| ## 📊 EAAI Benchmark Performance (150 Held-Out AI Debugging Scenarios) |
|
|
| | Model Baseline | Direct Code Leakage (↓) | Pedagogical Utility (1-5) (↑) | Conceptual Accuracy % (↑) | |
| | :--- | :---: | :---: | :---: | |
| | **Gemini 3.5 Flash (Google Frontier)** | **0.0%** | **4.79 / 5.0** | **98.7%** | |
| | **GPT-5.4-mini (Proprietary)** | **0.0%** | **4.67 / 5.0** | **98.7%** | |
| | **Socratic Muse-30B (SFT+DPO)** | **0.0%** | **4.75 / 5.0** | **90.0%** | |
| | **Socratic Llama-8B (SFT+DPO)** | **0.0%** | **3.54 / 5.0** | **76.0%** | |
| | Base Llama-3.1-8B-Instruct | 1.3% | 2.55 / 5.0 | 20.0% | |
| | Qwen2.5-Coder-7B-Instruct | 6.0% | 2.37 / 5.0 | 20.0% | |
|
|
| ## 📚 Dataset |
| The model was aligned on the **[Socratic AI Pedagogy Preference Dataset (1,680 Quadruplets)](https://huggingface.co/datasets/NextGenInstitute/socraticDataset1680)**. |
|
|
