AINeutralarXiv – CS AI · 7h ago6/10
🧠
Substrate Asymmetry in User-Side Memory: A Diagnostic Framework
Researchers reveal that large language model user-memory capabilities exhibit substrate asymmetry across three orthogonal dimensions—behavioral consistency, factual recall, and factual abstinence—with parametric methods (gamma-LoRA) excelling at style preservation while retrieval-augmented generation (RAG) excels at knowing when to abstain. The same neural circuits drive opposite-direction failures, and this tradeoff intensifies in heavily RLHF-tuned models, suggesting fundamental alignment costs to parametric personalization.
🧠 Llama