区分临床文本转SQL中模糊与模型不稳，提升错误诊断效率
Disentangling Ambiguity from Instability in Large Language Models: A Clinical Text-to-SQL Case Study
- 将文本转SQL分为理解与回答两阶段，拆解语义不确定性
- 高模糊高不稳场景占查询25%却含51%错误，可精准定位问题
- 提供诊断分解，指导针对性干预，优于单一不确定评分
在临床Text-to-SQL部署中，需区分输出多样性来自输入模糊（应触发澄清）还是模型不稳（应触发人工审核）。本文提出CLUES框架，将文本转SQL建模为两阶段过程（解释→答案），并分解语义不确定性为模糊度得分与不稳定性得分。不稳定性得分通过双部语义图矩阵的Schur补计算。在AmbigQA/SituatedQA（黄金解释）和临床Text-to-SQL基准（已知解释）上，CLUES在失败预测上优于当前最优的核语言熵方法。部署中表现稳定，并提供单一分数无法获得的诊断分解。不确定性区域对应不同干预策略：模糊时优化查询，不稳时改进模型。高模糊高不稳区域虽仅覆盖25%查询，却包含51%错误，实现高效故障排查。
原文摘要 · Abstract (English)
Deploying large language models for clinical Text-to-SQL requires distinguishing two qualitatively different causes of output diversity: (i) input ambiguity that should trigger clarification, and (ii) model instability that should trigger human review. We propose CLUES, a framework that models Text-to-SQL as a two-stage process (interpretations --> answers) and decomposes semantic uncertainty into an ambiguity score and an instability score. The instability score is computed via the Schur complement of a bipartite semantic graph matrix. Across AmbigQA/SituatedQA (gold interpretations) and a clinical Text-to-SQL benchmark (known interpretations), CLUES improves failure prediction over state-of-the-art Kernel Language Entropy. In deployment settings, it remains competitive while providing a diagnostic decomposition unavailable from a single score. The resulting uncertainty regimes map to targeted interventions - query refinement for ambiguity, model improvement for instability. The high-ambiguity/high-instability regime contains 51% of errors while covering 25% of queries, enabling efficient triage.
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。