#artificial intelligence
Jan 2026
OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents
This work proposes \textbf{Self-ReCheck}, a lightweight, model-agnostic memory filtering mechanism that mitigates over-personalization while preserving personalization performance in memory-augmented dialogue systems.
Yu-Lin Hu, Zi-Mo Long, Jiahe Guo et al.
· arXiv.org · 23 citations
· ⚡2