{"ID":5938065,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-07T23:54:33.395952201Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04061","arxiv_id":"2607.04061","title":"Telescope: Improving Zero Shot Detection of LLM Generated Content By Measuring Token Repetition Probability","abstract":"Distinguishing Large Language Model (LLM) generated text from human writing is a critical and difficult challenge. While LLMs are trained to write like humans, we hypothesize that this training leaves an indelible mark. LLMs develop a particularly strong aversion to token repetition very early in training. This bias persists as a ''Vestigial Heuristic'' (a developmental artifact) that is activated in LLM-generated text, separating LLM from human writing. To probe this phenomenon, we introduce Telescope Perplexity, a metric that evaluates the token repetition of the model, $P(s_i | s_{1:i})$ . Our empirical investigation reveals that the Telescope Perplexity signature emerges early in pre-training, and Telescope Perplexity empirically enables highly effective zero-shot LLM detection. We show state-of-the-art or competitive performance across diverse datasets (including modern evaluation sets we introduce), reference models, and perturbation schemes with greater efficiency than other methods.","short_abstract":"Distinguishing Large Language Model (LLM) generated text from human writing is a critical and difficult challenge. While LLMs are trained to write like humans, we hypothesize that this training leaves an indelible mark. LLMs develop a particularly strong aversion to token repetition very early in training. This bias pe...","url_abs":"https://arxiv.org/abs/2607.04061","url_pdf":"https://arxiv.org/pdf/2607.04061v1","authors":"[\"Christopher Nassif\",\"Josh F. Cooper\"]","published":"2026-07-05T00:13:12Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.LG\",\"stat.ML\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}