GEM achieves 65.19% joint goal accuracy on MultiWOZ 2.2 by routing between a graph neural network expert for dialogue structure and a T5 expert for sequences, plus ReAct agents for value generation, outperforming prior SOTA methods.
arXiv preprint arXiv:2109.08678 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
UniQGen is a constraint-guided LLM agent framework that generates accurate Cypher queries for KGQA, reporting F1 gains of 31.6% on GraphQ and 4.9% on GrailQA over prior methods without requiring fine-tuning.
citing papers explorer
-
GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking
GEM achieves 65.19% joint goal accuracy on MultiWOZ 2.2 by routing between a graph neural network expert for dialogue structure and a T5 expert for sequences, plus ReAct agents for value generation, outperforming prior SOTA methods.
-
Graph Query Generation with Constraint-guided Large Language Agents
UniQGen is a constraint-guided LLM agent framework that generates accurate Cypher queries for KGQA, reporting F1 gains of 31.6% on GraphQ and 4.9% on GrailQA over prior methods without requiring fine-tuning.