Search papers, labs, and topics across Lattice.
Affiliation:
2
0
4
0
SPEAR bridges the reasoning gap in reinforcement learning by transforming complex natural-language reasoning into efficient symbolic milestones, enabling dense and logical reward signals without costly neural verifiers.
Seemingly strong NLI checkers can actually *hurt* medical RAG training by collapsing the RL gradient or triggering reward-hacking cascades like ultra-short answers and search avoidance.
