Mohammad Reza Modarres, Armin Tourajmehr, Artin Tavasoli, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28434 · open-access PDF
Los modelos de idiomas grandes dejan rastros específicos de modelos en su texto generado, pero permanece incierto cuán finamente estas huellas dactilares pueden distinguir modelos relacionados y qué señales siguen siendo informativas a medida que se reducen las indicaciones obvias.Estudiamos esto a través de la resolución de huellas dactilares, considerando tanto la resolución del modelo, desde diferentes familias a variantes destiladas y adaptadas, como la resolución de la señal a través de evidencias comportamentales, estilométricas, léxicas y semánticas.
Machine translation (Meta M2M100); the English original follows.
Large language models leave model-specific traces in their generated text, but it remains unclear how finely these fingerprints can distinguish related models and which signals remain informative as obvious cues are reduced. We study this through fingerprint resolution, considering both model resolution, from different families to distilled and adapted variants, and signal resolution across behavioral, stylometric, lexical, and semantic evidence. We progressively suppress surface cues, paraphrase outputs, vary the amount of available text, and test generalization across prompt distributions an
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28434, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange