用化学启发的协作机制提升多大模型用药推荐可靠性
Multi-LLM Collaboration for Medication Recommendation
- 基于化学模型设计多大模型协作框架，减少幻觉与不一致
- 在真实临床场景中实现稳定且可信的个性化用药推荐
- 适合医疗AI系统研发者和临床决策支持团队参考
随着医疗领域日益依赖AI实现可扩展且可靠的临床决策支持，保障模型推理的可靠性仍是关键挑战。单个大语言模型（LLM）易产生幻觉和不一致，而简单的模型集成往往无法保证稳定性和可信度。基于我们此前关于LLM Chemistry的工作——量化大模型间的协作兼容性，本文将该框架应用于从简短临床病历中生成用药推荐。所提方法通过化学启发的交互建模，引导多模型协作，使集成具备有效性（发挥互补优势）、稳定性（输出一致质量）和校准性（减少干扰与错误放大）。我们在真实临床场景中评估了基于化学原理的多模型协作策略，探究其能否生成可信的、患者定制的用药建议。初步结果令人鼓舞，表明基于LLM Chemistry的协作可能为临床实践中可靠可信的AI助手提供可行路径。
原文摘要 · Abstract (English)
As healthcare increasingly turns to AI for scalable and trustworthy clinical decision support, ensuring reliability in model reasoning remains a critical challenge. Individual large language models (LLMs) are susceptible to hallucinations and inconsistency, whereas naive ensembles of models often fail to deliver stable and credible recommendations. Building on our previous work on LLM Chemistry, which quantifies the collaborative compatibility among LLMs, we apply this framework to improve the reliability in medication recommendation from brief clinical vignettes. Our approach leverages multi-LLM collaboration guided by Chemistry-inspired interaction modeling, enabling ensembles that are effective (exploiting complementary strengths), stable (producing consistent quality), and calibrated (minimizing interference and error amplification). We evaluate our Chemistry-based Multi-LLM collaboration strategy on real-world clinical scenarios to investigate whether such interaction-aware ensembles can generate credible, patient-specific medication recommendations. Preliminary results are encouraging, suggesting that LLM Chemistry-guided collaboration may offer a promising path toward reliable and trustworthy AI assistants in clinical practice.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。