arXiv：cs.AI· Sophia Mao, Keshav Gandhi, Alexander Gutfraind·· 6 小时前
大语言模型生成行为模式用于流行病学建模：多基准评估框架
Large language model-generated patterns for epidemiological modeling: a multi-benchmark evaluation framework
AI 导读
研究以丙肝病毒相关注射吸毒行为为案例，评估 LLM 生成的行为输出能否替代稀缺的实证行为数据。三个 LLM 在 28 项文献关联上的无条件方向还原率为 46-68%，而直接要求其分类相同关联时一致性达 82-93%；与 ABM 和调查相关性模式的平均绝对差分别为 0.11-0.13 和 0.15-0.18。LLM 生成的行为关系与流行病学证据仅部分对齐，纳入传播动力学模型前需更系统评估。
正文
Abstract:Representing individual-level behavioral heterogeneity is challenging in epidemiological modeling, particularly when empirical behavioral data are sparse. We assess the potential of large language model (LLM)-generated behavioral outputs in addressing this challenge, using hepatitis C virus-related behaviors among people who inject drugs as a case study. Correspondence with epidemiological patterns was evaluated using external benchmarks: literature-informed association directions, correlations from an agent-based model (ABM), and survey associations. Across three LLMs, unconditional directional recovery across 28 retained literature-informed associations was 46-68%, compared with 82-93% agreement when LLMs were directly asked to classify the same associations. Mean absolute differences from ABM and survey correlation patterns were 0.11-0.13 and 0.15-0.18, respectively. Together, these findings show partial alignment between LLM-generated behavioral relationships and epidemiological evidence, despite higher knowledge-probe agreement. More systematic evaluation is needed before incorporating LLM-generated behavioral outputs into epidemiological models that simulate transmission dynamics.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.15994 [cs.AI] |
| (or arXiv:2610.15994v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.15994 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sophia Mao [view email]
[v1]
Sun, 11 Oct 2026 23:48:02 UTC (263 KB)
来源：arXiv：cs.AI · arxiv.org