README.md

---
language: en
license: apache-2.0
tags:
  - ai-detection
  - lora
  - phi-3
  - llamafactory
base_model: microsoft/Phi-3-medium-128k-instruct
---

## 📘 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.

---

## 🚀 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/inverter" 

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 PI, text should in this format: "What is the prompt that generates the input text {text to-be-detected}?
text = "What is the prompt that generates the input text ... ?"
gen = model.generate(
    **inputs,
    output_scores=True,
    return_dict_in_generate=True
)

generated_text = tokenizer.decode(gen.sequences[0], skip_special_tokens=True)
print("Generated:", generated_text)
```

### 🧩 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}")
```

---

## 🚀 LLaMA-Factory Usage （Chat）
```python
llamafactory-cli chat examples/inference/distinguisher_ptcv.yaml
```
### Example lora_sft.yaml YAML configuration

```yaml
model_name_or_path: microsoft/Phi-3-medium-128k-instruct
adapter_name_or_path: bellafc/IPAD/Distinguisher_PTCV
template: phi
infer_backend: vllm
max_new_tokens: 128
temperature: 0.7
```

---

## 🚀 LLaMA-Factory Usage （API）
```python
llamafactory-cli api examples/inference/lora_sft.yaml
```
### Example lora_sft.yaml YAML configuration

```yaml
model_name_or_path: microsoft/Phi-3-medium-128k-instruct
adapter_name_or_path: bellafc/IPAD/Distinguisher_PTCV
template: phi
infer_backend: vllm
max_new_tokens: 128
temperature: 0.7
```
after that, run python distinguishers_testscript.py


## ⚙️ Model Details

| Property | Description |
|-----------|-------------|
| **Base model** | [`microsoft/Phi-3-medium-128k-instruct`](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct) |
| **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) |