快速思考,智能对话:结构化健康文本生成中确定性与神经计算的划分
Think Fast, Talk Smart: Partitioning Deterministic and Neural Computation for Structured Health Text Generation
AI总结:
提出一种将确定性计算与有限LLM调用相结合的流水线,用于结构化健康文本生成,在降低错误率和成本的同时保持忠实性。
摘要:
大型语言模型(LLM)越来越多地被用于从结构化记录(如可穿戴时间序列、生物标志物、生命体征和护理管理日志)生成健康文本。对于重复性健康输出,流畅性是不够的:系统必须忠实于源数据,将解释性主张建立在可用证据上,遵循既定政策,输出机器可读的内容,并且运行成本足够低以支持重复使用。我们探讨在结构化健康生成中,哪些责任应由确定性计算承担,而非运行时LLM提示。我们引入了“快速思考,智能对话”,一个睡眠健康洞察流水线,其中确定性代码在调用一次有界LLM写入器之前执行重复分析。在280个用户-夜晚和六个模型上,与结构化零样本和少样本单次调用基线相比,该方法实现了更低的数值误差、更低的指令合规误差和更低的端到端成本。层替换揭示了特定合约的失败:LLM比较增加了数值误差,LLM排名降低了策略选择,LLM属性增加了无根据的因果语言,而LLM生成的写入器接口即使在上游事实确定后也会重新引入误差。结果支持一个更广泛的设计规则:让代码负责重复分析,让LLM在有界接口内表达已验证的事实。
英文摘要:
Large language models (LLMs) are increasingly being used to generate health text from structured records such as wearable time series, biomarkers, vitals, and care-management logs. For recurring health outputs, fluency is not enough: systems must remain faithful to source data, ground explanatory claims in available evidence, follow stated policies, emit machine-readable outputs, and run cheaply enough for repeated use. We ask which responsibilities in structured health generation should be deterministic computation rather than runtime LLM prompting. We introduce Think Fast, Talk Smart, a sleep-health insight pipeline in which deterministic code performs recurring analysis before one bounded LLM writer call. Across 280 user-nights and six models, achieves lower numeric error, lower instruction-compliance error, and lower end-to-end cost than structured zero-shot and few-shot one-call baselines. Layer replacement reveals contract-specific failures: LLM comparison raises numeric error, LLM ranking degrades policy selection, LLM attribution increases unsupported causal language, and an LLM-generated writer interface reintroduces errors even after upstream facts are deterministic. The results support a broader design rule: let code own recurring analysis, and let LLMs express verified facts within bounded interfaces.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。