A category-bounded LLM memory system for in-car voice assistants achieves .78 to .95 F1 for preference extraction, 92 to 95 percent reduction of redundant and contradictory stored preferences, and .87 retrieval accuracy on the new synthetic CarMem dataset.
MP: Avoidance of Specific Road Types • Attributes: Highways, Toll roads, Unpaved roads ii
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CarMem: Enhancing Long-Term Memory in LLM Voice Assistants through Category-Bounding
A category-bounded LLM memory system for in-car voice assistants achieves .78 to .95 F1 for preference extraction, 92 to 95 percent reduction of redundant and contradictory stored preferences, and .87 retrieval accuracy on the new synthetic CarMem dataset.