Update README.md

README.md

@@ -1,26 +1,64 @@
 ---
 license: mit
 ---
+
 # SQL Socratic Models
 
-This repository contains fine-tuned LLMs for Text-to-SQL using Socratic prompting and reasoning decomposition.
+This repository contains fine-tuned large language models for **Socratic SQL instruction** in higher education, focusing on guiding learners through SQL concepts using structured reasoning rather than providing direct solutions.
 
 ## Models
 - phi3_rq4
 - qwen25
-- llama31
+- gemma2
 
 ## Method
-We fine-tune models on SQL generation tasks with Socratic reasoning prompts.
+
+Our approach is designed to support **conceptual learning in STEM education** through Socratic interaction:
+
+- **Phase 1 (Data Construction):**  
+  SQL instruction data is augmented with Socratic prompts emphasizing:
+  - Question decomposition  
+  - Conceptual hints  
+  - Guided reasoning steps  
+
+- **Phase 2 (Fine-Tuning):**  
+  We apply full fine-tuning (FFT) on small, open-source LLMs with **pedagogical constraints** that explicitly discourage direct answer generation and instead promote:
+  - Conceptual scaffolding  
+  - Incremental reasoning  
+  - Learner-centered guidance  
+
+- **Phase 3 (Evaluation):**  
+  Models are evaluated using:
+  - **BERTScore** for semantic alignment with expected reasoning  
+  - **ROUGE-L** to measure and control **answer leakage** (i.e., avoidance of direct SQL solutions)
 
 ## Contributions
-- Fine-tuning across multiple architectures
-- Ablation studies on reasoning components
-- Evaluation on Text-to-SQL benchmarks
+- Fine-tuning across multiple architectures (Phi-3, Qwen2.5, Gemma2) for **instructional SQL reasoning**
+- Development of **Socratic SQL prompting framework** for higher education contexts
+- Evaluation of models on their ability to generate **guidance without revealing final answers**
+- Ablation study identifying factors that enable LLMs to mimic effective instructors through:
+  - Misconception-aware feedback  
+  - Iterative questioning  
+  - Structured reasoning support  
+
+## Task
+
+Given a natural language SQL question, the model generates:
+
+1. Socratic reasoning steps  
+2. Conceptual hints and guiding questions  
+3. Intermediate decomposition of the problem  
+
+**The model does NOT produce the final SQL query**, ensuring alignment with instructional use in higher education settings.
+
+This design supports:
+- Active learning  
+- Conceptual understanding of SQL  
+- Integration of database concepts into broader STEM curricula  
 
 ## Usage
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 model = AutoModelForCausalLM.from_pretrained("sriram882004/SQL-Socratic-Models/phi3_rq4")
-tokenizer = AutoTokenizer.from_pretrained(...)
+tokenizer = AutoTokenizer.from_pretrained("sriram882004/SQL-Socratic-Models/phi3_rq4")