{"ID":2894974,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.10475","arxiv_id":"2507.10475","title":"Can You Detect the Difference?","abstract":"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.","short_abstract":"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)...","url_abs":"https://arxiv.org/abs/2507.10475","url_pdf":"https://arxiv.org/pdf/2507.10475v1","authors":"[\"İsmail Tarım\",\"Aytuğ Onan\"]","published":"2025-07-14T16:55:57Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Diffusion Model\",\"Large Language Model\",\"Language Model\"]","has_code":false}