OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents
This addresses the issue of inappropriate personalization for users of conversational agents, though it is incremental as it builds on existing memory-augmented systems.
The paper tackles the problem of over-personalization in memory-augmented conversational agents, where agents inappropriately use personal information, and introduces OP-Bench, a benchmark of 1,700 instances, finding that over-personalization is widespread and proposing Self-ReCheck to mitigate it while preserving performance.
Memory-augmented conversational agents enable personalized interactions using long-term user memory and have gained substantial traction. However, existing benchmarks primarily focus on whether agents can recall and apply user information, while overlooking whether such personalization is used appropriately. In fact, agents may overuse personal information, producing responses that feel forced, intrusive, or socially inappropriate to users. We refer to this issue as \emph{over-personalization}. In this work, we formalize over-personalization into three types: Irrelevance, Repetition, and Sycophancy, and introduce \textbf{OP-Bench} a benchmark of 1,700 verified instances constructed from long-horizon dialogue histories. Using \textbf{OP-Bench}, we evaluate multiple large language models and memory-augmentation methods, and find that over-personalization is widespread when memory is introduced. Further analysis reveals that agents tend to retrieve and over-attend to user memories even when unnecessary. To address this issue, we propose \textbf{Self-ReCheck}, a lightweight, model-agnostic memory filtering mechanism that mitigates over-personalization while preserving personalization performance. Our work takes an initial step toward more controllable and appropriate personalization in memory-augmented dialogue systems.