Disentangling Ambiguity from Instability in Large Language Models: A Clinical Text-to-SQL Case Study

Angelo Ziletti, Leonardo D’Ambrosi


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.
Anthology ID:
2026.clinicalnlp-1.39
Volume:
Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Asma Ben Abacha, Steven Bethard, Danielle Bitterman, Tristan Naumann, Kirk Roberts
Venues:
ClinicalNLP | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
369–380
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-clinicalnlp-39
DOI:
10.63317/4qse3ioqyh8s
Bibkey:
Cite (ACL):
Angelo Ziletti and Leonardo D’Ambrosi. 2026. Disentangling Ambiguity from Instability in Large Language Models: A Clinical Text-to-SQL Case Study. In Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026, pages 369–380, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Disentangling Ambiguity from Instability in Large Language Models: A Clinical Text-to-SQL Case Study (Ziletti & D’Ambrosi, ClinicalNLP 2026)
Copy Citation: