LLM reasoning / chain-of-thought

GNNs

Superseded baseline#332 of 772 most-superseded

Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here

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