ConceptSearch uses LLM-generated programs with concept-based scoring to solve 29/50 ARC training tasks and speed up search by up to 30% versus pixel-distance scoring.
In Pro- ceedings of the 2019 Conference on Empirical Methods in Natural Language Processing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ConceptSearch: Towards Efficient Program Search Using LLMs for Abstraction and Reasoning Corpus (ARC)
ConceptSearch uses LLM-generated programs with concept-based scoring to solve 29/50 ARC training tasks and speed up search by up to 30% versus pixel-distance scoring.