不用微调，用搜索策略自动安排摘要控制顺序。
Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search
- 用蒙特卡洛树搜索规划属性调整顺序，逐步优化
- 1B小模型效果接近70B大模型，多属性控制更稳定
- 适合需要灵活调整摘要风格的研究者和开发者
可控摘要超越通用输出，依据指定属性生成符合人类意图的摘要。实际中属性间存在依赖关系，语言模型难以一致满足相关约束。以往方法常需针对每个属性微调，灵活性受限。本文提出PACO框架——一种无需训练的多属性可控摘要自适应规划方法，将任务重构为基于定制蒙特卡洛树搜索（MCTS）的顺序控制规划。节点代表摘要，动作对应单属性调整，仅对需修正的属性进行渐进式优化。该策略自适应发现最优控制顺序，最终生成满足所有约束的摘要。跨多个领域与模型的大量实验表明，PACO在多属性可控性上表现优异，优于基于大模型自规划及微调基线。值得注意的是，使用Llama-3.2-1B的PACO在可控性上媲美更大规模的Llama-3.3-70B基线；使用更大模型时，其控制性能全面超越所有对手。
原文摘要 · Abstract (English)
Controllable summarization moves beyond generic outputs toward human-aligned summaries guided by specified attributes. In practice, the interdependence among attributes makes it challenging for language models to satisfy correlated constraints consistently. Moreover, previous approaches often require per-attribute fine-tuning, limiting flexibility across diverse summary attributes. In this paper, we propose adaptive planning for multi-attribute controllable summarization (PACO), a training-free framework that reframes the task as planning the order of sequential attribute control with a customized Monte Carlo Tree Search (MCTS). In PACO, nodes represent summaries, and actions correspond to single-attribute adjustments, enabling progressive refinement of only the attributes requiring further control. This strategy adaptively discovers optimal control orders, ultimately producing summaries that effectively meet all constraints. Extensive experiments across diverse domains and models demonstrate that PACO achieves robust multi-attribute controllability, surpassing both LLM-based self-planning models and fine-tuned baselines. Remarkably, PACO with Llama-3.2-1B rivals the controllability of the much larger Llama-3.3-70B baselines. With larger models, PACO achieves superior control performance, outperforming all competitors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。