PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants
This addresses the problem of evaluating personalization in task-oriented AI assistants for researchers and developers, though it is incremental as it builds on existing benchmarking and LLM-as-a-Judge paradigms.
The authors tackled the lack of systematic evaluation for personalization in conversational AI assistants by introducing PersonaLens, a benchmark that reveals significant variability in the personalization capabilities of current LLM assistants across diverse tasks.
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.