RTSoG combines question decomposition, LLM-reward-guided Monte Carlo Tree Search with a self-critic stop signal, and weighted path stacking to achieve new state-of-the-art KGQA accuracy, though without code or error bars.
Dbpedia: A nucleus for a web of open data,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing Large Language Models with Reward-guided Tree Search for Knowledge Graph Question and Answering
RTSoG combines question decomposition, LLM-reward-guided Monte Carlo Tree Search with a self-critic stop signal, and weighted path stacking to achieve new state-of-the-art KGQA accuracy, though without code or error bars.