让大模型像专家一样一步步推理决策，结果更准且可解释。
DecisionFlow: Advancing Large Language Model as Principled Decision Maker
- 构建结构化决策空间，用隐式效用函数评估权衡
- 在两个高风险任务上准确率比基线最高提升30%
- 适合医疗、金融等需透明决策的场景
在医疗、金融等高风险领域，有效决策不仅需要准确结果，还需透明可解释的推理过程。现有语言模型常以孤立、事后的方式生成决策与理由，缺乏系统性思考。为此，我们提出DecisionFlow框架，引导模型基于动作、属性和约束的结构化表示进行推理。不同于直接从提示中预测答案，DecisionFlow构建语义基础的决策空间，并推断隐式效用函数，以效用驱动方式评估权衡，使决策与可解释理由紧密耦合。在两个高风险基准上的实证结果显示，DecisionFlow相比强基线最多提升30%准确率，同时增强结果对齐性。本工作是将符号推理与大模型融合的关键一步，推动更可问责、可解释、可靠的决策支持系统发展。代码与数据见https://github.com/xiusic/DecisionFlow。
原文摘要 · Abstract (English)
In high-stakes domains such as healthcare and finance, effective decision-making demands not just accurate outcomes but transparent and explainable reasoning. However, current language models often lack the structured deliberation needed for such tasks, instead generating decisions and justifications in a disconnected, post-hoc manner. To address this, we propose DecisionFlow, a novel decision modeling framework that guides models to reason over structured representations of actions, attributes, and constraints. Rather than predicting answers directly from prompts, DecisionFlow builds a semantically grounded decision space and infers a latent utility function to evaluate trade-offs in a transparent, utility-driven manner. This process produces decisions tightly coupled with interpretable rationales reflecting the model's reasoning. Empirical results on two high-stakes benchmarks show that DecisionFlow not only achieves up to 30% accuracy gains over strong prompting baselines but also enhances alignment in outcomes. Our work is a critical step toward integrating symbolic reasoning with LLMs, enabling more accountable, explainable, and reliable LLM decision support systems. Code and data are at https://github.com/xiusic/DecisionFlow.
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。