A two-stage LLM system that retrieves structured attributes and user reviews, filters the useful knowledge type via LLM probes, and separates intent reasoning from response generation outperforms prior methods on MMConv.
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
-
Dual Knowledge-Enhanced Two-Stage Reasoner for Multimodal Dialog Systems
A two-stage LLM system that retrieves structured attributes and user reviews, filters the useful knowledge type via LLM probes, and separates intent reasoning from response generation outperforms prior methods on MMConv.