Large reasoning models underperform general chat models on personalization tasks, but a structured template plus self-checking and self-referencing restores and improves performance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reasoning Meets Personalization: Unleashing the Potential of Large Reasoning Model for Personalized Generation
Large reasoning models underperform general chat models on personalization tasks, but a structured template plus self-checking and self-referencing restores and improves performance.