Disentangling Ambiguity from Instability in Large Language Models: A Clinical Text-to-SQL Case Study
Year: 2026
Type: conference-paper
Abstract: 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.
Authors: Angelo Ziletti, Leonardo D'Ambrosi
Institution: Bayer (Germany)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166553366