Newest papers

CALLIOPE: Private Insights into AI Use, Without Embeddings

Edith Cohen, Vadym Doroshenko, Badih Ghazi, Charlie Harrison, Pritish Kamath, Alexander Knop, Ravi Kumar, Ethan Leeman · 2026 · arXiv

DOI: 10.48550/arXiv.2610.28797 · open-access PDF

Spanish

Introducimos CALLIOPE, un marco top-down para descubrir jerarquías de temas en grandes corporaciones de datos no estructurados (por ejemplo, conversaciones LLM), mientras que soporta la privacidad diferencial (DP). A diferencia de los enfoques LLM-augmentados tradicionales e incluso recientes que en última instancia se basan en la agrupación de incorporaciones vectoriales, nuestro marco aprovecha las capacidades de LLM directamente para todo el tubo. Los experimentos demuestran que este enfoque proporciona una mejor utilidad sobre los métodos existentes (basados en la incorporación) en el entorno DP, especialmente en el régimen de alta privacidad.

Machine translation (Meta M2M100); the English original follows.

Abstract

We introduce CALLIOPE, a top-down framework for discovering topic hierarchies in large corpora of unstructured data (e.g., LLM conversations), while supporting differential privacy (DP). Unlike traditional and even recent LLM-augmented approaches that ultimately rely on clustering vector embeddings, our framework leverages LLM capabilities directly for the entire pipeline. Experiments demonstrate that this approach provides better utility over existing (embedding-based) methods in the DP setting, especially in the high privacy regime. We evaluate the quality of CALLIOPE outputs using a variety

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28797, 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.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange