LLM reasoning / chain-of-thought
LUNA: Learning Slot-Turn Alignment for Dialogue State Tracking
Superseded — cited as a baseline and beaten by newer methods
0 papers critique it · 1 beat it on benchmarks
Head-to-head results where a newer method reports beating LUNA. Values are copied from the source paper's tables — verify against the cited paper.
GEM (BERT_base + GNN) / T5_small + Claude 3.7 S. beats LUNA
65.19 vs 56.13
JGA · [Multi-domain DST on MultiWOZ 2.2]