Metraipolis › archive › dc_b9c8da665bc9
Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration — arXiv:2608.05741
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.05741
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-25T21:27:13.705Z
- SHA-256 of the archived text
214f167395c6682baa5266d6b8f8312d6afc5ce1ea8ff9bc1410d553d8f5ee8e- Stable URL of this page
https://metraipolis.com/documento/dc_b9c8da665bc9
How to cite
Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration — arXiv:2608.05741 — arXiv (en), https://arxiv.org/abs/2608.05741 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b9c8da665bc9 (Metraipolis archive dc_b9c8da665bc9, sha256 214f167395c6682baa5266d6b8f8312d6afc5ce1ea8ff9bc1410d553d8f5ee8e)
BibTeX
@misc{dcb9c8da665bc9,
title = {Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration — arXiv:2608.05741},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.05741},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b9c8da665bc9; sha256 214f167395c6682baa5266d6b8f8312d6afc5ce1ea8ff9bc1410d553d8f5ee8e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05741. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) can generate fluent and convincing text at scale, creating growing risks for misinformation dissemination, educational misuse, and platform governance. These concerns make robust detection of machine-generated text increasingly necessary. Recent zero-shot detectors mainly exploit probability-based statistical discrepancies, but they do not explicitly account for the training process of LLMs, which leaves a distinct generation mechanism insufficiently modeled and limits detection robustness. To address this issue, we propose EchoPrompt, a training-free detector based on latent prompt restoration. Our key intuition is that machine-generated text is typically produced conditioned on an upstream prompt, and this hidden dependency can be partially reactivated by prepending a unified generic prefix. Specifically, EchoPrompt restores a generic assistant-response context, measures the induced likelihood gain with an instruction-tuned model, calibrates it against the corresponding base model, and aggregates the resulting differences into a score that quantifies latent prompt dependency. Extensive experiments show that EchoPrompt achieves state-of-the-art performance among zero-shot detectors while maintaining strong robustness across challenging evaluation settings. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.05741 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-25T21:24:38.203Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).