用可执行代码评估解释质量，提升不确定环境下导航效率
Effective Explanations Support Planning Under Uncertainty
- 将解释转化为可执行的策略与价值地图，支持规划
- 高质量解释使导航成功率提高27%，减少重规划次数
- 适合研究人机交互、智能助手与可解释决策系统者
解释如何从A点到达B点具有挑战性，需预判听者基于信息会采取的行动。为此，我们提出一种计算模型：大语言模型将解释转换为程序化指导（策略先验与价值图），规划代理在部分可观测条件下执行。通过路径效率与可靠性评分，惩罚重规划行为。在四项预注册实验中，收集了24张地图上的1200条解释，获取帮助度评价，测量基线导航表现，并测试不同质量解释下的行为表现。高分解释被评价更有效，显著提升导航效果：使用解释的参与者优于无解释组，高质量解释比低质量解释带来更大改善。结果表明，程序性解释是受效用驱动的沟通形式，其有效性取决于语言在不确定性下能否落地为行动。
原文摘要 · Abstract (English)
Explaining how to get from A to B can be challenging. It requires mentally simulating what the listener will do based on what they are told. To capture this process, we propose a computational model that converts utterances into action plans: a large language model translates an explanation into program-like guidance (a policy prior and value map), and a planning agent executes it under partial observability. We score explanations by the efficiency and reliability of the resulting paths, penalizing replanning. Across four preregistered experiments, we collect a corpus of 1,200 explanations over 24 maps, elicit helpfulness judgments, measure baseline navigation, and test behavior with explanations of differing quality. Higher-scored explanations are judged more helpful and improve navigation: participants with explanations outperform those without, and high-scoring explanations help more than low-scoring ones. Together, these results show procedural explanation as utility-guided communication shaped by how language can be grounded into action under uncertainty.
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。