Update README.md

README.md

@@ -1,3 +1,103 @@
----
-license: unknown
----
+# 🧠 IPAD — Inverse Prompt for AI Detection
+
+> **Fine-tuned Phi-3-Medium-128k-Instruct with LoRA using [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory)**  
+> Author: [@bellafc](https://huggingface.co/bellafc)
+
+---
+
+## 📘 Overview
+
+Large Language Models (LLMs) have achieved human-level fluency in text generation, making it increasingly difficult to distinguish between human- and AI-authored content.  
+**IPAD (Inverse Prompt for AI Detection)** introduces a two-stage detection framework:
+
+1. **Prompt Inverter** — predicts the underlying prompts that could have generated an input text.  
+2. **Distinguisher** — evaluates the alignment between the text and its predicted prompts to determine whether it was AI-generated.
+
+All **Prompt Inverter**, **Distinguisher (RC)** and **Distinguisher (PTCV)** are **LoRA-fine-tuned versions** of  
+[`microsoft/Phi-3-medium-128k-instruct`](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct),  
+trained using [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory) for **robust AI text detection** under diverse and adversarial conditions.
+
+- 🧩 **Distinguisher (RC)** — optimized for regular, unstructured text inputs (baseline detection).  
+- 🔬 **Distinguisher (PTCV)** — specialized for *structured, compositional, or OOD* data, exhibiting enhanced robustness.
+
+---
+
+## ⚙️ Model Details
+
+| Property | Description |
+|-----------|-------------|
+| **Base model** | [`microsoft/Phi-3-medium-128k-instruct`](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct) |
+| **Architecture** | Decoder-only Transformer |
+| **Fine-tuning** | LoRA (rank-8, α=16, dropout=0.05) |
+| **Context length** | 128k tokens |
+| **Framework** | [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory) |
+| **Task** | AI Text Detection (Discriminator) |
+| **Language** | English |
+| **License** | Apache 2.0 |
+| **Author** | [@bellafc](https://huggingface.co/bellafc) |
+
+---
+
+## 🚀 Quick Usage
+
+### 🧩 Prompt Inverter
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+base_model = "microsoft/Phi-3-medium-128k-instruct"
+lora_model = "bellafc/IPAD/Distinguisher_PTCV"  # or Distinguisher_RC
+
+tokenizer = AutoTokenizer.from_pretrained(base_model)
+model = AutoModelForCausalLM.from_pretrained(base_model, torch_dtype="auto", device_map="auto")
+model = PeftModel.from_pretrained(model, lora_model)
+
+# For RC, text should in this format: "Can LLM generate the input text {text to-be detected} through the prompt {prompt generated by Prompt Inverter (PI)}?"
+# For PTCV, text should in this format: "Text2 is generated by LLM, determine whether text1 is also generated by LLM with a similar prompt. Text1: {text to-be detected}. Text2: {Regenerated text}"
+
+text = "Text2 is generated by LLM, determine whether text1 is also generated by LLM with a similar prompt. Text1: ... . Text2: ... ."
+gen = model.generate(
+    **inputs,
+    max_new_tokens=10,
+    output_scores=True,
+    return_dict_in_generate=True
+)
+
+generated_text = tokenizer.decode(gen.sequences[0], skip_special_tokens=True)
+probs = softmax(gen.scores[0], dim=-1)
+yes_token_id = tokenizer(" yes", add_special_tokens=False).input_ids[0]
+print("Generated:", generated_text)
+print(f"P('yes') = {probs[0, yes_token_id].item():.4f}")
+```
+
+### 🧩 Distinguishers
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+base_model = "microsoft/Phi-3-medium-128k-instruct"
+lora_model = "bellafc/IPAD/Distinguisher_PTCV"  # or Distinguisher_RC
+
+tokenizer = AutoTokenizer.from_pretrained(base_model)
+model = AutoModelForCausalLM.from_pretrained(base_model, torch_dtype="auto", device_map="auto")
+model = PeftModel.from_pretrained(model, lora_model)
+
+# For RC, text should in this format: "Can LLM generate the input text {text to-be detected} through the prompt {prompt generated by Prompt Inverter (PI)}?"
+# For PTCV, text should in this format: "Text2 is generated by LLM, determine whether text1 is also generated by LLM with a similar prompt. Text1: {text to-be detected}. Text2: {Regenerated text}"
+
+text = "Text2 is generated by LLM, determine whether text1 is also generated by LLM with a similar prompt. Text1: ... . Text2: ... ."
+gen = model.generate(
+    **inputs,
+    max_new_tokens=10,
+    output_scores=True,
+    return_dict_in_generate=True
+)
+
+generated_text = tokenizer.decode(gen.sequences[0], skip_special_tokens=True)
+probs = softmax(gen.scores[0], dim=-1)
+yes_token_id = tokenizer(" yes", add_special_tokens=False).input_ids[0]
+print("Generated:", generated_text)
+print(f"P('yes') = {probs[0, yes_token_id].item():.4f}")
+```