---
id: 20260913-T0-07
title: "临床计算怕出错？新方法让LLM做确定性数学求解"
title_en: "New Method Makes LLMs Deterministic Math Solvers for Clinical Use"
url: https://ai.daily.yangsir.net/daily/20260913-T0-07
issue_date: 2026-09-13
publish_date: 2026-09-12T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2609.10728
---

# 临床计算怕出错？新方法让LLM做确定性数学求解

LLM在算术上不可靠，而临床计算器中一个数字错误就可能改变医疗建议。传统做法是将每个计算器逐个硬编码为验证函数，效率低下。研究者提出一种确定性数学求解方法，让临床语言模型能够可靠执行计算任务。这有望让医疗机构更安全地部署LLM辅助工具，减少因计算错误导致的临床风险。

## English Version

**New Method Makes LLMs Deterministic Math Solvers for Clinical Use**

LLMs are unreliable at arithmetic, and a single numerical error in clinical calculators can change medical recommendations. The standard approach hardcodes each calculator as a validated function one at a time, which is inefficient. Researchers propose a deterministic math solver method that enables clinical language models to reliably perform computational tasks. This could help medical institutions deploy LLM-assisted tools more safely and reduce clinical risks from calculation errors.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2609.10728)

**详情页**：https://ai.daily.yangsir.net/daily/20260913-T0-07

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*