EpiNarrate: Agentic Generation of Grounded Narratives from Epidemiological Scenario Projections

EpiNarrate：基于流行病学情景预测的智能叙事生成框架

Abstract: Generation of clear and accessible public health narratives is critical for communicating complex epidemiological projections to policymakers and the general public at large. Such narratives require more than simply reporting numbers: projections must be contextualized and quantitatively grounded across multiple dimensions. 摘要： 生成清晰且易于理解的公共卫生叙事，对于向政策制定者和广大公众传达复杂的流行病学预测至关重要。此类叙事不仅仅是简单的数据报告：预测结果必须在多个维度上进行情境化处理，并具备坚实的定量依据。

Further, projections are often derived from large ensemble datasets which combine intervention assumptions, geographic and demographic strata, outcomes, time horizons, and uncertainty quantiles. However, directly using large language models (LLMs) to summarize and contextualize such data often leads to inconsistencies, omissions, and fragile behavior. 此外，预测结果通常源自大型集成数据集，这些数据集结合了干预假设、地理和人口统计层级、结果、时间跨度以及不确定性分位数。然而，直接使用大语言模型（LLM）来总结和情境化此类数据，往往会导致逻辑不一致、信息遗漏以及模型表现不稳定等问题。

We introduce an agentic framework (EpiNarrate) for public health report generation that separates structured numerical reasoning from natural-language generation. The framework first extracts scenario axes and organizes them into a partial-order schema, enabling systematic traversal of the underlying multidimensional space. 我们引入了一个用于公共卫生报告生成的智能体框架（EpiNarrate），该框架将结构化数值推理与自然语言生成分离开来。该框架首先提取情景轴，并将其组织成偏序模式，从而实现对底层多维空间的系统性遍历。

It then constructs an augmented dataset and derives valid quantitative statements through a comparison grammar that enforces semantic and arithmetic consistency. To balance coverage and non-redundancy, we introduce an interestingness-driven selection mechanism based on maximum-entropy principles. 随后，它通过一种强制执行语义和算术一致性的比较语法，构建增强数据集并推导出有效的定量陈述。为了平衡覆盖范围与非冗余性，我们引入了一种基于最大熵原理的“趣味性驱动”选择机制。

Experiments on the COVID-19 Scenario Modeling Hub demonstrate that our model produces narratives with improved factual grounding and broader coverage of salient epidemiological patterns, while preserving the style of expert-written reports. 在 COVID-19 情景建模中心（COVID-19 Scenario Modeling Hub）进行的实验表明，我们的模型生成的叙事在事实依据上更扎实，对显著流行病学模式的覆盖更全面，同时保持了专家撰写报告的专业风格。