# Clio: Privacy-Preserving Insights into Real-World AI Use

arXiv: https://arxiv.org/abs/2412.13678 · HTML: https://mlsanity.com/paper/2412.13678/

## Key facts

- Cited by 72 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 104 references that are in the map.
- First posted on arXiv 18 Dec 2024.

## Builds on (most cited first, 27 of 27)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://mlsanity.com/paper/2209.07858/) (2022)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://mlsanity.com/paper/2312.02003/) (2023)
- [Understanding Dataset Difficulty with V-Usable Information](https://mlsanity.com/paper/2110.08420/) (2021)
- [What Does it Mean for a Language Model to Preserve Privacy?](https://mlsanity.com/paper/2202.05520/) (2022)
- [Security and Privacy Challenges of Large Language Models: A Survey](https://mlsanity.com/paper/2402.00888/) (2024)
- [Sociotechnical Safety Evaluation of Generative AI Systems](https://mlsanity.com/paper/2310.11986/) (2023)
- [Harms from Increasingly Agentic Algorithmic Systems](https://mlsanity.com/paper/2302.10329/) (2023)
- [The Ethics of AI Ethics -- An Evaluation of Guidelines](https://mlsanity.com/paper/1903.03425/) (2019)
- [The Ethics of Advanced AI Assistants](https://mlsanity.com/paper/2404.16244/) (2024)
- [The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization](https://mlsanity.com/paper/2202.00443/) (2022)
- [Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooM](https://mlsanity.com/paper/2404.12259/) (2024)
- [Privacy in Deep Learning: A Survey](https://mlsanity.com/paper/2004.12254/) (2020)
- [Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness](https://mlsanity.com/paper/2010.01285/) (2020)
- [Privacy Issues in Large Language Models: A Survey](https://mlsanity.com/paper/2312.06717/) (2023)
- [Goal-Driven Explainable Clustering via Language Descriptions](https://mlsanity.com/paper/2305.13749/) (2023)
- [Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild](https://mlsanity.com/paper/2407.11438/) (2024)
- [The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions](https://mlsanity.com/paper/2310.12418/) (2023)
- [TnT-LLM: Text Mining at Scale with Large Language Models](https://mlsanity.com/paper/2403.12173/) (2024)
- [First-Person Fairness in Chatbots](https://mlsanity.com/paper/2410.19803/) (2024)
- [The Use of Generative Search Engines for Knowledge Work and Complex Tasks](https://mlsanity.com/paper/2404.04268/) (2024)
- [The Role of Governments in Increasing Interconnected Post-Deployment Monitoring of AI](https://mlsanity.com/paper/2410.04931/) (2024)

## Built on by (most cited first, 30 of 72)

- [GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks](https://mlsanity.com/paper/2510.04374/) (2025)
- [Organize the Web: Constructing Domains Enhances Pre-Training Data Curation](https://mlsanity.com/paper/2502.10341/) (2025)
- [Toward an Evaluation Science for Generative AI Systems](https://mlsanity.com/paper/2503.05336/) (2025)
- [The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It](https://mlsanity.com/paper/2505.24119/) (2025)
- [EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees](https://mlsanity.com/paper/2503.08893/) (2025)
- [How AI Impacts Skill Formation](https://mlsanity.com/paper/2601.20245/) (2026)
- [CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactions](https://mlsanity.com/paper/2508.01674/) (2025)
- [HiBayES: A Hierarchical Bayesian Modeling Framework for AI Evaluation Statistics](https://mlsanity.com/paper/2505.05602/) (2025)
- [Detecting Safety Violations Across Many Agent Traces](https://mlsanity.com/paper/2604.11806/) (2026)
- [Generative Value Conflicts Reveal LLM Priorities](https://mlsanity.com/paper/2509.25369/) (2025)
- [The Lock-in Hypothesis: Stagnation by Algorithm](https://mlsanity.com/paper/2506.06166/) (2025)
- [Culture is Everywhere: A Call for Intentionally Cultural Evaluation](https://mlsanity.com/paper/2509.01301/) (2025)
- [Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment](https://mlsanity.com/paper/2602.16660/) (2026)
- [Benchmarking Misuse Mitigation Against Covert Adversaries](https://mlsanity.com/paper/2506.06414/) (2025)
- [The Pluralistic Moral Gap: Understanding Judgment and Value Differences between Humans and Large Language Models](https://mlsanity.com/paper/2507.17216/) (2025)
- [DiscoverLLM: From Executing Intents to Discovering Them](https://mlsanity.com/paper/2602.03429/) (2026)
- [Real-World Gaps in AI Governance Research](https://mlsanity.com/paper/2505.00174/) (2025)
- [LLMs unlock new paths to monetizing exploits](https://mlsanity.com/paper/2505.11449/) (2025)
- [Can Large Language Models Really Recognize Your Name?](https://mlsanity.com/paper/2505.14549/) (2025)
- [Urania: Differentially Private Insights into AI Use](https://mlsanity.com/paper/2506.04681/) (2025)
- [When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration](https://mlsanity.com/paper/2506.05579/) (2025)
- [Attention to Non-Adopters](https://mlsanity.com/paper/2510.15951/) (2025)
- [Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms](https://mlsanity.com/paper/2601.20131/) (2026)
- [Automatically Finding Reward Model Biases](https://mlsanity.com/paper/2602.15222/) (2026)
- [Implicit Turn-Wise Policy Optimization for Proactive User-LLM Interaction](https://mlsanity.com/paper/2603.23550/) (2026)
- [Dataset Featurization: Uncovering Natural Language Features through Unsupervised Data Reconstruction](https://mlsanity.com/paper/2502.17541/) (2025)
- [Societal Impacts Research Requires Benchmarks for Creative Composition Tasks](https://mlsanity.com/paper/2504.06549/) (2025)
- [HERCULES: Hierarchical Embedding-based Recursive Clustering Using LLMs for Efficient Summarization](https://mlsanity.com/paper/2506.19992/) (2025)
- [Show or Tell? Modeling the evolution of request-making in Human-LLM conversations](https://mlsanity.com/paper/2508.01213/) (2025)
- [Evalet: Evaluating Large Language Models through Functional Fragmentation](https://mlsanity.com/paper/2509.11206/) (2025)

## Abstract (arXiv)

How are AI assistants being used in the real world? While model providers in theory have a window into this impact via their users' data, both privacy concerns and practical challenges have made analyzing this data difficult. To address these issues, we present Clio (Claude insights and observations), a privacy-preserving platform that uses AI assistants themselves to analyze and surface aggregated usage patterns across millions of conversations, without the need for human reviewers to read raw conversations. We validate this can be done with a high degree of accuracy and privacy by conducting extensive evaluations. We demonstrate Clio's usefulness in two broad ways. First, we share insights about how models are being used in the real world from one million Claude.ai Free and Pro conversations, ranging from providing advice on hairstyles to providing guidance on Git operations and concepts. We also identify the most common high-level use cases on Claude.ai (coding, writing, and research tasks) as well as patterns that differ across languages (e.g., conversations in Japanese discuss elder care and aging populations at higher-than-typical rates). Second, we use Clio to make our systems safer by identifying coordinated attempts to abuse our systems, monitoring for unknown unknowns during critical periods like launches of new capabilities or major world events, and improving our existing monitoring systems. We also discuss the limitations of our approach, as well as risks and ethical concerns. By enabling analysis of real-world AI usage, Clio provides a scalable platform for empirically grounded AI safety and governance.