An LLM and evolutionary prompt tuning discover a compact set of programs whose node mappings yield tight upper bounds to GED, trained without any ground-truth GED labels.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GRAIL: Graph Edit Distance and Node Alignment Using LLM-Generated Code
An LLM and evolutionary prompt tuning discover a compact set of programs whose node mappings yield tight upper bounds to GED, trained without any ground-truth GED labels.