RASPberry: Retrieval-Augmented Monte Carlo Tree Self-Play with Reasoning Consistency for Multi-Hop Question Answering.

Baixuan Li, Yunlong Fan, Tianyi Ma, Miao Gao, Chuanqi Shi, Zhiqiang Gao

06 Jan 2026 (modified: 06 Jan 2026)ACL (Findings) 2025EveryoneRevisionsCC BY-SA 4.0
Loading