PersonaLens uses LLM-simulated users and an LLM judge to evaluate personalization in task-oriented conversational assistants across 111 tasks and 20 domains.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants
PersonaLens uses LLM-simulated users and an LLM judge to evaluate personalization in task-oriented conversational assistants across 111 tasks and 20 domains.