PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants

TL;DR

PersonaLens is a new benchmark designed to evaluate how well conversational AI assistants personalize interactions in task-oriented settings, addressing limitations of existing benchmarks that focus on non-task domains.

Contribution

We introduce PersonaLens, a comprehensive benchmark with diverse user profiles and specialized agents to systematically assess personalization in task-oriented AI assistants.

Findings

Current LLM assistants show high variability in personalization capabilities.

PersonaLens reveals gaps in personalization across different tasks.

Benchmark facilitates targeted improvements in conversational AI personalization.

Abstract

Large language models (LLMs) have advanced conversational AI assistants. However, systematically evaluating how well these assistants apply personalization--adapting to individual user preferences while completing tasks--remains challenging. Existing personalization benchmarks focus on chit-chat, non-conversational tasks, or narrow domains, failing to capture the complexities of personalized task-oriented assistance. To address this, we introduce PersonaLens, a comprehensive benchmark for evaluating personalization in task-oriented AI assistants. Our benchmark features diverse user profiles equipped with rich preferences and interaction histories, along with two specialized LLM-based agents: a user agent that engages in realistic task-oriented dialogues with AI assistants, and a judge agent that employs the LLM-as-a-Judge paradigm to assess personalization, response quality, and task success. Through extensive experiments with current LLM assistants across diverse tasks, we reveal significant variability in their personalization capabilities, providing crucial insights for advancing conversational AI systems.