CALLIOPE: Private Insights into AI Use, Without Embeddings

Researchers posted CALLIOPE to arXiv on 20 Oct 2026, a top-down framework that uses LLMs directly across the entire pipeline to discover topic hierarchies in large unstructured corpora such as LLM conversations while supporting differential privacy. The authors report that CALLIOPE delivers better utility than existing embedding-based methods in the DP setting, especially in the high privacy regime, and evaluate its outputs with traditional clustering metrics plus novel utility metrics they introduce. The work matters because it offers a way to surface insights into AI use without relying on vector embeddings.

Computer Science Machine Learning Submitted on 20 Oct 2026 Title:CALLIOPE: Private Insights into AI Use, Without Embeddings View PDF https://arxiv.org/pdf/2610.28797 HTML experimental https://arxiv.org/html/2610.28797v1 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 of traditionally studied clustering metrics, as well as some novel utility metrics that we introduce. Additional Features Current browse context: cs.LG References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender IArxiv Recommender What is IArxiv? https://iarxiv.org/about arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .