Method Drift›LLM reasoning / chain-of-thought
Superseded baseline#332 of 772 most-superseded
GNNs
LLM reasoning / chain-of-thought
superseded — cited as a baseline and beaten by newer methods
1 papers critique it · 0 beat it on benchmarks
What papers say
Verbatim critique sentences, each from a paper that cites GNNs as a baseline.
“GNNs show promise for modeling complex relational structures, yet their application to dialogue understanding remains underdeveloped.”
— GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking