# PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data

arXiv: https://arxiv.org/abs/2502.20616 · HTML: https://mlsanity.com/paper/2502.20616/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 14 of its 27 references that are in the map.
- First posted on arXiv 28 Feb 2025.

## Placed in

- Retrieval-augmented generation / [Privacy and security of RAG](https://mlsanity.com/rag/privacy-and-security-of-rag/)

## Builds on (most cited first, 14 of 14)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://mlsanity.com/paper/2407.18901/) (2024)
- [Social Simulacra: Creating Populated Prototypes for Social Computing Systems](https://mlsanity.com/paper/2208.04024/) (2022)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [Personalized Language Modeling from Personalized Human Feedback](https://mlsanity.com/paper/2402.05133/) (2024)
- [You Impress Me: Dialogue Generation via Mutual Persona Perception](https://mlsanity.com/paper/2004.05388/) (2020)
- [Personalizing Dialogue Agents via Meta-Learning](https://mlsanity.com/paper/1905.10033/) (2019)
- [UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systems](https://mlsanity.com/paper/2401.13256/) (2024)
- [ERAGent: Enhancing Retrieval-Augmented Language Models with Improved Accuracy, Efficiency, and Personalization](https://mlsanity.com/paper/2405.06683/) (2024)

## Built on by (most cited first, 27 of 27)

- [Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale](https://mlsanity.com/paper/2504.14225/) (2025)
- [Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2505.15957/) (2025)
- [MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models](https://mlsanity.com/paper/2507.12806/) (2025)
- [HorizonBench: Long-Horizon Personalization with Evolving Preferences](https://mlsanity.com/paper/2604.17283/) (2026)
- [Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions](https://mlsanity.com/paper/2602.22680/) (2026)
- [PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments](https://mlsanity.com/paper/2603.23231/) (2026)
- [VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions](https://mlsanity.com/paper/2605.27141/) (2026)
- [Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval](https://mlsanity.com/paper/2510.08935/) (2025)
- [Towards Natural Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactions](https://mlsanity.com/paper/2603.04191/) (2026)
- [How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistants](https://mlsanity.com/paper/2601.16621/) (2026)
- [Towards Faithful and Controllable Personalization via Critique-Post-Edit Reinforcement Learning](https://mlsanity.com/paper/2510.18849/) (2025)
- [MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment Simulation](https://mlsanity.com/paper/2606.02470/) (2026)
- [Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory](https://mlsanity.com/paper/2605.00702/) (2026)
- [LUNAR: Benchmarking Personalized Large Language Models on UNiversal User BehAvioR Logs](https://mlsanity.com/paper/2608.05246/) (2026)
- [Learning What to Share and What to Personalize: Hierarchical Strategy Co-Evolution for Agent Memory](https://mlsanity.com/paper/2608.25329/) (2026)
- [Opal: Private Memory for Personal AI](https://mlsanity.com/paper/2604.02522/) (2026)
- [StreamProfileBench: A Benchmark for Fine-Grained User Profile Inference in Real-World Streaming Scenarios](https://mlsanity.com/paper/2605.25758/) (2026)
- [From Profiling to Synthesis: Benchmarking Implicit Behavioral Alignment in Personalized LLM Agents](https://mlsanity.com/paper/2608.02171/) (2026)
- [PersonaTrace: Synthesizing Realistic Digital Footprints with LLM Agents](https://mlsanity.com/paper/2603.11955/) (2026)
- [BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces](https://mlsanity.com/paper/2606.02798/) (2026)
- [ProfileFoundry: A Synthetic Person-Object Substrate for Privacy, Memory, and Tool-Use Evaluation in LLM Agent](https://mlsanity.com/paper/2606.26403/) (2026)
- [When Thinking Before Retrieval Hurts: TraceBound Diagnostics for Adaptive Knowledge-Graph Retrieval](https://mlsanity.com/paper/2607.24800/) (2026)
- [No PUN Intended: Plausible Unknown Names for Person-Centred LLM Evaluation](https://mlsanity.com/paper/2608.21206/) (2026)
- [ThinkFlow: Self-Evolving Probabilistic Latent Memory for Lifelong Conversational Agents](https://mlsanity.com/paper/2609.17010/) (2026)
- [AMU:Admission and Memory Update for Personalized Conversations---Structured Memory with SLM Guided Control](https://mlsanity.com/paper/2609.36976/) (2026)
- [Gradient-Aligned Pair Selection for Personalized Preference Optimization](https://mlsanity.com/paper/2610.00061/) (2026)
- [ToolRACER: A Robust Agentic Conversation Emulation Resource for Agent Training and Evaluation](https://mlsanity.com/paper/2610.09163/) (2026)

## Abstract (arXiv)

Personalization is critical in AI assistants, particularly in the context of private AI models that work with individual users. A key scenario in this domain involves enabling AI models to access and interpret a user's private data (e.g., conversation history, user-AI interactions, app usage) to understand personal details such as biographical information, preferences, and social connections. However, due to the sensitive nature of such data, there are no publicly available datasets that allow us to assess an AI model's ability to understand users through direct access to personal information. To address this gap, we introduce a synthetic data generation pipeline that creates diverse, realistic user profiles and private documents simulating human activities. Leveraging this synthetic data, we present PersonaBench, a benchmark designed to evaluate AI models' performance in understanding personal information derived from simulated private user data. We evaluate Retrieval-Augmented Generation (RAG) pipelines using questions directly related to a user's personal information, supported by the relevant private documents provided to the models. Our results reveal that current retrieval-augmented AI models struggle to answer private questions by extracting personal information from user documents, highlighting the need for improved methodologies to enhance personalization capabilities in AI.