Llama-3-8B-Instruct-HIP-adapter

Llama-3-8B-Instruct-HIP-adapter

This repository contains a LoRA adapter trained for Humanization by Iterative Paraphrasing (HIP), from the paper Base Models Look Human To AI Detectors.

The adapter is intended to be loaded on top of:

meta-llama/Meta-Llama-3-8B-Instruct

Model Details

• Adapter type: LoRA / PEFT adapter
• Base model: meta-llama/Meta-Llama-3-8B-Instruct
• Training objective: AI-to-human paraphrase reconstruction
• Training data: paired AI-style and human-written passages from the HIP training data
• Intended pipeline: iterative paraphrasing, where the adapter rewrites the previous round's output for a fixed number of rounds

Intended Use

This adapter is released to support research reproducibility for the HIP paper. It is intended for studying detector behavior, paraphrase-based rewriting, and robustness of AI-text detectors.

The adapter should not be used to evade deployed academic-integrity, authorship, or provenance systems in real-world settings.

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base_model = "meta-llama/Meta-Llama-3-8B-Instruct"
adapter = "YixuanEvenXu/Llama-3-8B-Instruct-HIP-adapter"

tokenizer = AutoTokenizer.from_pretrained(adapter)
model = AutoModelForCausalLM.from_pretrained(base_model, device_map="auto")
model = PeftModel.from_pretrained(model, adapter)

For the full minimal HIP pipeline, see the code release linked from the paper.

Training Summary

The adapter was trained with supervised fine-tuning on paired examples (a_i, h_i), where a_i is an AI-style paraphrase of a human passage and h_i is the corresponding human-written target. Training uses a plain source-target format rather than a chat template.

Citation

If you use this adapter, please cite:

@article{xu2026base,
  title={Base Models Look Human To AI Detectors},
  author={Yixuan Even Xu and Ziqian Zhong and Aditi Raghunathan and Fei Fang and J. Zico Kolter},
  journal={arXiv preprint arXiv:2605.19516},
  year={2026}
}

License and Terms

This adapter is built on top of Meta Llama 3 materials and is distributed under the Meta Llama 3 Community License. Users must comply with the Meta Llama 3 license and acceptable use policy for the base model.

Built with Meta Llama 3.

Base model reference:

meta-llama/Meta-Llama-3-8B-Instruct

Limitations

This adapter was trained for a specific research setting and evaluated on selected English prose domains. Performance may differ across domains, languages, detectors, and future detector versions.