AIBullisharXiv – CS AI · 18h ago6/10
🧠
LEAF: Growing Trees Without Branching for Speech-Aware Large Language Model Post-Training
LEAF (Low-rank Exploration with Adaptive Forking) introduces a novel tree-based reinforcement learning method for training speech-aware large language models that improves credit assignment by identifying shared response prefixes and assigning rewards at the span level rather than uniformly across tokens. The approach achieves superior performance compared to existing GRPO-style methods without requiring additional computational overhead, enabling smaller models to match or exceed larger baselines.