Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search
This addresses the problem of flexible and consistent multi-attribute control in summarization for users needing tailored outputs, representing a novel method rather than an incremental improvement.
The paper tackles the challenge of generating summaries that satisfy multiple correlated attributes consistently, proposing a training-free framework called PACO that uses Monte Carlo Tree Search to adaptively plan attribute control order, achieving robust multi-attribute controllability and outperforming baselines, with PACO using Llama-3.2-1B rivaling the controllability of Llama-3.3-70B baselines.
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.