Pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.AI 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

Mitigating Over-Personalization in LLMs via Structured Memory

cs.AI · 2026-08-08 · conditional · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Mitigating Over-Personalization in LLMs via Structured Memory cs.AI · 2026-08-08 · conditional · none · ref 7

    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.