Method Drift›LLM reasoning / chain-of-thought
Superseded baseline#565 of 772 most-superseded
RAG and KG prompting
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superseded — cited as a baseline and beaten by newer methods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 RAG and KG prompting as a baseline.
“While more sophisticated knowledge fusion techniques like RAG and KG prompting have demonstrated improved performance, they still face challenges with retrieval accuracy and computational efficiency”
— GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking