Edith Cohen, Vadym Doroshenko, Badih Ghazi, Charlie Harrison, Pritish Kamath, Alexander Knop, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, Mikhail Pravilov, Adam Sealfon, Yurii Sushko, Marika Swanberg, Chiyuan Zhang · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.28797 · cited by 0 works (OpenAlex) · open-access PDF
Kami memperkenalkan CALLIOPE, kerangka kerja top-down untuk menemukan hierarki topik dalam corpora besar data yang tidak terstruktur (misalnya, percakapan LLM), sambil mendukung privasi diferensial (DP). Tidak seperti pendekatan LLM tradisional dan bahkan baru-baru ini yang diperluas yang pada akhirnya bergantung pada embeddings vektor cluster, kerangka kerja kami memanfaatkan kemampuan LLM secara langsung untuk seluruh pipa. Eksperimen menunjukkan bahwa pendekatan ini memberikan utilitas yang lebih baik atas metode yang ada (berbasis embedding) dalam pengaturan DP, terutama dalam rezim privasi tinggi. Kami mengevaluasi kualitas output CALLIOPE menggunakan berbagai metrik cluster tradisional yang dipelajari, serta beberapa metrik utilitas baru yang kami memperkenalkan.
Machine translation (Meta M2M100); the English original follows.
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 of traditionally studied clustering metrics, as well as some novel utility metrics that we introduce.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Variety (cybernetics), Computer science, Cluster analysis, Differential privacy, Artificial intelligence, Conceptual clustering
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.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange