Method Drift›LLM reasoning / chain-of-thought
Superseded baseline#632 of 772 most-superseded
semantic parsing
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superseded — cited as a baseline and beaten by newer methods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 semantic parsing as a baseline.
“semantic parsing often produces non-executable queries due to syntactic constraints”
— GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking