Grouping a user's stored memories into domain-labeled sections before injecting them into an LLM's context reduces cross-domain leakage by 8.8 percentage points on average across seven models, while slightly improving beneficial memory use.
he/him” for Troy. A later memory then states: “She began weekly therapy sessions on Tuesdays at 4 pm starting January 23, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mitigating Over-Personalization in LLMs via Structured Memory
Grouping a user's stored memories into domain-labeled sections before injecting them into an LLM's context reduces cross-domain leakage by 8.8 percentage points on average across seven models, while slightly improving beneficial memory use.