Two new research papers address the challenge of over-personalization in large language models (LLMs). The first paper, "Mitigating Over-Personalization in LLMs via Structured Memory," proposes an inference-time modification to how memories are presented to the model, partitioning them by domain to reduce cross-domain leakage and memory-induced sycophancy. The second paper, "SPRInG: Continual LLM Personalization via Selective Parametric Adaptation and Retrieval-Interpolated Generation," introduces a semi-parametric framework that uses drift-driven selective adaptation to identify genuine preference shifts and fuses parametric knowledge with retrieved history for more robust continual personalization. AI
IMPACT These papers offer new techniques to improve the reliability and adaptability of personalized LLMs, addressing key challenges in their real-world deployment.
RANK_REASON Two academic papers published on arXiv presenting novel methods for LLM personalization.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
