# Can You Detect the Difference?

arXiv: https://arxiv.org/abs/2507.10475 · HTML: https://mlsanity.com/paper/2507.10475/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 17 references that are in the map.
- First posted on arXiv 14 Jul 2025.

## Builds on (most cited first, 9 of 9)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [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)
- [A Robust Semantics-based Watermark for Large Language Model against Paraphrasing](https://mlsanity.com/paper/2311.08721/) (2023)
- [DAMAGE: Detecting Adversarially Modified AI Generated Text](https://mlsanity.com/paper/2501.03437/) (2025)
- [Improved Unbiased Watermark for Large Language Models](https://mlsanity.com/paper/2502.11268/) (2025)
- [In-Context Watermarks for Large Language Models](https://mlsanity.com/paper/2505.16934/) (2025)

## Built on by (most cited first, 1 of 1)

- [Watermarking Diffusion Language Models](https://mlsanity.com/paper/2509.24368/) (2025)

## Abstract (arXiv)

The rapid advancement of large language models (LLMs) has raised concerns about reliably detecting AI-generated text. Stylometric metrics work well on autoregressive (AR) outputs, but their effectiveness on diffusion-based models is unknown. We present the first systematic comparison of diffusion-generated text (LLaDA) and AR-generated text (LLaMA) using 2 000 samples. Perplexity, burstiness, lexical diversity, readability, and BLEU/ROUGE scores show that LLaDA closely mimics human text in perplexity and burstiness, yielding high false-negative rates for AR-oriented detectors. LLaMA shows much lower perplexity but reduced lexical fidelity. Relying on any single metric fails to separate diffusion outputs from human writing. We highlight the need for diffusion-aware detectors and outline directions such as hybrid models, diffusion-specific stylometric signatures, and robust watermarking.