Upload 8 files

README.md

@@ -1,3 +1,36 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+language:
+- en
+metrics:
+- roc_auc
+base_model:
+- EleutherAI/gpt-neo-2.7B
+pipeline_tag: text-classification
+tags:
+- machine-text-detection
+- machine-revised-text-detection
+---
+
+<h1 align="center">Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection</h1>
+
+<p align="center">
+   <a href="https://scholar.google.com/citations?user=Au_y5poAAAAJ">Jiaqi Chen</a><sup>*</sup>, <a href="https://xyzhu1225.github.io/">Xiaoye Zhu</a><sup>*</sup>, <a href="https://leolty.github.io/">Tianyang Liu</a><sup>*</sup>, Ying Chen, <a href="https://xinhuichen-02.github.io/">Xinhui Chen</a>,<br> <a href="https://scholar.google.com/citations?user=koA9QbMAAAAJ">Yiwen Yuan</a>, <a href="https://cooperleong00.github.io/">Chak Tou Leong</a>, <a href="https://zcli-charlie.github.io/">Zuchao Li</a><sup>†</sup>, Tang Long, <a href="https://yusalei.github.io/">Lei Zhang</a>, <br><a href="https://scholar.google.com/citations?user=281EWzQAAAAJ">Chenyu Yan</a>, <a href="https://scholar.google.com/citations?user=mliv6KEAAAAJ">Guanghao Mei</a>, <a href="https://scholar.google.com/citations?user=epTfECgAAAAJ">Jie Zhang</a><sup>†</sup>, <a href="https://scholar.google.com/citations?user=BLKHwNwAAAAJ">Lefei Zhang</a><sup>†</sup>
+</p>
+
+<p align="center">
+  *Equal contribution.<br> †Equal contribution of corresponding author.
+</p>
+
+Detecting **machine-revised text** remains a challenging task as it often involves subtle style changes embedded within human-originated content. The ImBD framework introduces a novel approach to tackle this problem, leveraging **style preference optimization (SPO)** and **Style-CPC** to effectively capture machine-style phrasing. Our method achieves state-of-the-art performance in detecting revisions by open-source and proprietary LLMs like GPT-3.5 and GPT-4o, demonstrating significant efficiency with minimal training data.
+
+We are excited to share our code and data to support further exploration in detecting machine-revised text. We welcome your feedback and invite collaborations to advance this field together!
+
+
+![Main Figure](https://machine-text-detection.github.io/ImBD/static/images/method.png)
+
+## 🔥 News
+- **[2024, Dec 16]** Our online [demo](https://huggingface.co/spaces/machine-text-detection/ImBD) is available on hugging-face now!
+- **[2024, Dec 13]** Our [model](https://huggingface.co/xyzhu1225/ImBD/tree/main) and local inference code are available.
+- **[2024, Dec 9]** 🎉🎉 Our paper has been accepted by AAAI 25! 
+- **[2024, Dec 7]** We've released our [website](https://machine-text-detection.github.io/ImBD).

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./models/gpt-neo-2.7B",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77d90811cd85cf114444c8df70fc092d3cfedb1c9d12243618e5ed5fa45b3c75
+size 10503408

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}