# Origin Tracing and Detecting of LLMs

arXiv: https://arxiv.org/abs/2304.14072 · HTML: https://mlsanity.com/paper/2304.14072/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 39 references that are in the map.
- First posted on arXiv 27 Apr 2023.

## Builds on (most cited first, 30 of 30)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [GLM-130B: An Open Bilingual Pre-trained Model](https://mlsanity.com/paper/2210.02414/) (2022)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Defending Against Neural Fake News](https://mlsanity.com/paper/1905.12616/) (2019)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents](https://mlsanity.com/paper/1804.05685/) (2018)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [Weight Poisoning Attacks on Pre-trained Models](https://mlsanity.com/paper/2004.06660/) (2020)
- [CLUE: A Chinese Language Understanding Evaluation Benchmark](https://mlsanity.com/paper/2004.05986/) (2020)
- [Automatic Detection of Machine Generated Text: A Critical Survey](https://mlsanity.com/paper/2011.01314/) (2020)
- [The DeepFake Detection Challenge (DFDC) Dataset](https://mlsanity.com/paper/2006.07397/) (2020)
- [Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning](https://mlsanity.com/paper/2108.13888/) (2021)
- [Real or Fake? Learning to Discriminate Machine from Human Generated Text](https://mlsanity.com/paper/1906.03351/) (2019)
- [On the Possibilities of AI-Generated Text Detection](https://mlsanity.com/paper/2304.04736/) (2023)
- [A Span-Extraction Dataset for Chinese Machine Reading Comprehension](https://mlsanity.com/paper/1810.07366/) (2018)
- [Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence](https://mlsanity.com/paper/2209.02970/) (2022)
- [CSL: A Large-scale Chinese Scientific Literature Dataset](https://mlsanity.com/paper/2209.05034/) (2022)
- [LOT: A Story-Centric Benchmark for Evaluating Chinese Long Text Understanding and Generation](https://mlsanity.com/paper/2108.12960/) (2021)

## Built on by (most cited first, 30 of 40)

- [Who Wrote this Code? Watermarking for Code Generation](https://mlsanity.com/paper/2305.15060/) (2023)
- [DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text](https://mlsanity.com/paper/2305.17359/) (2023)
- [A Robust Semantics-based Watermark for Large Language Model against Paraphrasing](https://mlsanity.com/paper/2311.08721/) (2023)
- [Detecting Multimedia Generated by Large AI Models: A Survey](https://mlsanity.com/paper/2402.00045/) (2024)
- [A Survey on Detection of LLMs-Generated Content](https://mlsanity.com/paper/2310.15654/) (2023)
- [SeqXGPT: Sentence-Level AI-Generated Text Detection](https://mlsanity.com/paper/2310.08903/) (2023)
- [GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick](https://mlsanity.com/paper/2402.12948/) (2024)
- [HuRef: HUman-REadable Fingerprint for Large Language Models](https://mlsanity.com/paper/2312.04828/) (2023)
- [Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models](https://mlsanity.com/paper/2402.18059/) (2024)
- [HowkGPT: Investigating the Detection of ChatGPT-generated University Student Homework through Context-Aware Perplexity Analysis](https://mlsanity.com/paper/2305.18226/) (2023)
- [Detecting AI-Generated Text: Factors Influencing Detectability with Current Methods](https://mlsanity.com/paper/2406.15583/) (2024)
- [Watermarking LLMs with Weight Quantization](https://mlsanity.com/paper/2310.11237/) (2023)
- [AI-generated text boundary detection with RoFT](https://mlsanity.com/paper/2311.08349/) (2023)
- [Ten Words Only Still Help: Improving Black-Box AI-Generated Text Detection via Proxy-Guided Efficient Re-Sampling](https://mlsanity.com/paper/2402.09199/) (2024)
- [Spotting AI's Touch: Identifying LLM-Paraphrased Spans in Text](https://mlsanity.com/paper/2405.12689/) (2024)
- [DALD: Improving Logits-based Detector without Logits from Black-box LLMs](https://mlsanity.com/paper/2406.05232/) (2024)
- [Zero-Shot Detection of LLM-Generated Text using Token Cohesiveness](https://mlsanity.com/paper/2409.16914/) (2024)
- [LLM-Detector: Improving AI-Generated Chinese Text Detection with Open-Source LLM Instruction Tuning](https://mlsanity.com/paper/2402.01158/) (2024)
- [Incentivizing Quality Text Generation via Statistical Contracts](https://mlsanity.com/paper/2406.11118/) (2024)
- [Who Taught You That? Tracing Teachers in Model Distillation](https://mlsanity.com/paper/2502.06659/) (2025)
- [Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection](https://mlsanity.com/paper/2510.08602/) (2025)
- [DART: An AIGT Detector using AMR of Rephrased Text](https://mlsanity.com/paper/2412.11517/) (2024)
- [When Detection Fails: The Power of Fine-Tuned Models to Generate Human-Like Social Media Text](https://mlsanity.com/paper/2506.09975/) (2025)
- [Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs](https://mlsanity.com/paper/2510.05148/) (2025)
- [How Sampling Affects the Detectability of Machine-written texts: A Comprehensive Study](https://mlsanity.com/paper/2510.13681/) (2025)
- [MOSAIC: Multiple Observers Spotting AI Content](https://mlsanity.com/paper/2409.07615/) (2024)
- [Unveiling Large Language Models Generated Texts: A Multi-Level Fine-Grained Detection Framework](https://mlsanity.com/paper/2410.14231/) (2024)
- [Minimizing Mismatch Risk: A Prototype-Based Routing Framework for Zero-shot LLM-generated Text Detection](https://mlsanity.com/paper/2602.01240/) (2026)
- [Beyond the Final Actor: Modeling the Dual Roles of Creator and Editor for Fine-Grained LLM-Generated Text Detection](https://mlsanity.com/paper/2604.04932/) (2026)
- [Kill two birds with one stone: generalized and robust AI-generated text detection via dynamic perturbations](https://mlsanity.com/paper/2504.21019/) (2025)

## Abstract (arXiv)

The extraordinary performance of large language models (LLMs) heightens the importance of detecting whether the context is generated by an AI system. More importantly, while more and more companies and institutions release their LLMs, the origin can be hard to trace. Since LLMs are heading towards the time of AGI, similar to the origin tracing in anthropology, it is of great importance to trace the origin of LLMs. In this paper, we first raise the concern of the origin tracing of LLMs and propose an effective method to trace and detect AI-generated contexts. We introduce a novel algorithm that leverages the contrastive features between LLMs and extracts model-wise features to trace the text origins. Our proposed method works under both white-box and black-box settings therefore can be widely generalized to detect various LLMs.(e.g. can be generalized to detect GPT-3 models without the GPT-3 models). Also, our proposed method requires only limited data compared with the supervised learning methods and can be extended to trace new-coming model origins. We construct extensive experiments to examine whether we can trace the origins of given texts. We provide valuable observations based on the experimental results, such as the difficulty level of AI origin tracing, and the AI origin similarities, and call for ethical concerns of LLM providers. We are releasing all codes and data as a toolkit and benchmark for future AI origin tracing and detecting studies. footnoteWe are releasing all available resource at urlhttps://github.com/OpenLMLab/.