Utilizing Large Language Models (LLMs) for handling scientific information comes with risk of the outputs not matching expectations, commonly called hallucinations. To fully utilize LLMs in research requires improving their accuracy, avoiding hallucinations, and extending their scope to research topics outside their direct training. There is also a benefit to getting the most accurate information from an LLM at the time of inference without having to create and train custom new models for each application. Here, augmented generation and machine learning driven prompt optimization are combined to extract performance improvements over base LLM function on a common chemical research task. Specifically, an LLM was used to predict the topological polar surface area (TPSA) of molecules. By using augmented generation and machine learning optimized prompts, the error in the prediction was reduced to 7.44 root mean squared error (RMSE) from 59.41 RMSE with direct calls to the same LLM.

中文翻译：

---

增强和编程优化的 LLM 提示减少化学幻觉


使用大型语言模型 （LLMs） 来处理科学信息会带来输出与预期不符的风险，通常称为幻觉。要在研究中充分利用 LLMs 需要提高其准确性，避免幻觉，并将其范围扩展到直接培训之外的研究主题。在推理时从 LLM，而无需为每个应用程序创建和训练自定义新模型。在这里，增强生成和机器学习驱动的提示优化相结合，以提取常见化学研究任务中基本 LLM。具体来说，LLM 用于预测分子的拓扑极性表面积 （TPSA）。通过使用增强生成和机器学习优化提示，直接调用相同的 LLM）。