DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing
This addresses the issue of low diversity in creative writing tasks for users of LLMs, representing an incremental improvement over existing methods.
The paper tackled the problem of reduced output diversity in reinforcement learning-enhanced large language models for creative writing by proposing a framework with Diverse Planning Branching and group-aware diversity rewards, resulting in significantly improved diversity without compromising quality and outperforming baselines.
Reinforcement learning (RL)-based enhancement of large language models (LLMs) often leads to reduced output diversity, undermining their utility in open-ended tasks like creative writing. Current methods lack explicit mechanisms for guiding diverse exploration and instead prioritize optimization efficiency and performance over diversity. This paper proposes an RL framework structured around a semi-structured long Chain-of-Thought (CoT), in which the generation process is decomposed into explicitly planned intermediate steps. We introduce a Diverse Planning Branching method that strategically introduces divergence at the planning phase based on diversity variation, alongside a group-aware diversity reward to encourage distinct trajectories. Experimental results on creative writing benchmarks demonstrate that our approach significantly improves output diversity without compromising generation quality, consistently outperforming existing baselines.