GAPD adds dense token-level guidance from gold actions to outcome-based RL for KBQA via mid-anchor matching and outperforms SOTA on WebQSP, GrailQA, and GraphQ.
Preprint, arXiv:2603.00511
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GAPD: Gold-Action Policy Distillation for Agentic Reinforcement Learning in Knowledge Base Question Answering
GAPD adds dense token-level guidance from gold actions to outcome-based RL for KBQA via mid-anchor matching and outperforms SOTA on WebQSP, GrailQA, and GraphQ.