EpiNarrate: Agentic Generation of Grounded Narratives from Epidemiological Scenario Projections

• URL: http://arxiv.org/abs/2607.15544v1
• Date: Fri, 17 Jul 2026 01:30:50 GMT
• Title: EpiNarrate: Agentic Generation of Grounded Narratives from Epidemiological Scenario Projections
• Abstract summary: We introduce an agentic framework (EpiNarrate) for public health report generation.<n>EpiNarrate separates structured numerical reasoning from natural-language generation.<n>It first extracts scenario axes and organizes them into a partial-order schema.<n>It then constructs an augmented dataset and derives valid quantitative statements.
• Score: 15.376330927742474
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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. 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. 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. 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. 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.

Related papers

• Beyond Time Series: Spatial Reasoning for Epidemic Forecasting via Multimodal Learning [50.948271066372826]
  We introduce a spatially structured multimodal epidemic forecasting setting that integrates region-level temporal surveillance data with spatially localized auxiliary signals.<n>We evaluate our approach on real-world COVID-19, influenza, and influenza-like illness (IIL) forecasting tasks under realistic real-time evaluation protocols.
  arXiv  Detail & Related papers  (2026-06-20T17:58:17Z)
• WhatsApp Vaccine Discourse (WhaVax): An Expert-Annotated Dataset and Benchmark for Health Misinformation Detection [0.0]
  We introduce WhaVax, a new expert-annotated dataset of vaccine-related WhatsApp messages collected from large Brazilian public groups spanning multiple pandemic years.<n>We provide a detailed characterization of WhatsApp misinformation, revealing distinctive linguistic, structural, lexical, temporal, and group-level patterns.<n>We also benchmark classical models, fine-tuned Small Language Models, and zero- or few-shot Large Language Models under realistic data-scarcity constraints.
  arXiv  Detail & Related papers  (2026-03-25T14:54:09Z)
• On the Out-of-Distribution Generalization of Reasoning in Multimodal LLMs for Simple Visual Planning Tasks [56.98385132295952]
  We evaluate how well chain-of-thought approaches generalize on a simple planning task.<n>We find that reasoning traces which combine multiple text formats yield the best (and non-trivial) OOD generalization.<n> purely text-based models consistently outperform those utilizing image-based inputs.
  arXiv  Detail & Related papers  (2026-02-17T09:51:40Z)
• When Does Multimodality Lead to Better Time Series Forecasting? [96.26052272121615]
  We investigate whether and under what conditions such multimodal integration consistently yields gains.<n>Our findings reveal that the benefits of multimodality are highly condition-dependent.<n>Our study offers a rigorous, quantitative foundation for understanding when multimodality can be expected to aid forecasting tasks.
  arXiv  Detail & Related papers  (2025-06-20T23:55:56Z)
• HC-LLM: Historical-Constrained Large Language Models for Radiology Report Generation [89.3260120072177]
  We propose a novel Historical-Constrained Large Language Models (HC-LLM) framework for Radiology report generation.<n>Our approach extracts both time-shared and time-specific features from longitudinal chest X-rays and diagnostic reports to capture disease progression.<n> Notably, our approach performs well even without historical data during testing and can be easily adapted to other multimodal large models.
  arXiv  Detail & Related papers  (2024-12-15T06:04:16Z)
• Mental Disorder Classification via Temporal Representation of Text [33.47304614659701]
  Mental disorder prediction from social media posts is challenging due to the complexities of sequential text data. We propose a novel framework which compresses the large sequence of chronologically ordered social media posts into a series of numbers. We demonstrate the generalization capabilities of our framework by outperforming the current SOTA in three different mental conditions.
  arXiv  Detail & Related papers  (2024-06-15T10:53:21Z)
• Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation [59.138470433237615]
  We introduce statistical metrics that quantify both the linguistic and visual skew of a dataset for relational learning. We show that systematically controlled metrics are strongly predictive of generalization performance. This work informs an important direction towards quality-enhancing the data diversity or balance to scaling up the absolute size.
  arXiv  Detail & Related papers  (2024-03-25T03:18:39Z)
• Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling [53.7117640028211]
  We present a geometry-constrained probabilistic modeling treatment to resolve the identified issues. We incorporate a suite of critical geometric properties to impose proper constraints on the layout of constructed embedding space. A spectral graph-theoretic method is devised to estimate the number of potential novel classes.
  arXiv  Detail & Related papers  (2024-03-02T00:56:05Z)
• Structured Time Series Prediction without Structural Prior [0.152292571922932]
  Time series prediction is a widespread and well studied problem with applications in many domains. We propose a fully data-driven model which does not rely on such a graph, nor any other prior structural information.
  arXiv  Detail & Related papers  (2022-02-07T22:01:58Z)
• Discrepancies in Epidemiological Modeling of Aggregated Heterogeneous Data [1.433758865948252]
  We show that state-of-the-art models for estimating epidemiological parameters, e.g.transmission rates, can be inappropriate when faced with complex systems. We generate three complex outbreak scenarios by combining incidence curves from multiple epidemics. We evaluate two data-generating models within this Bayesian inference framework.
  arXiv  Detail & Related papers  (2021-06-20T03:41:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.