Sensitivity Uncertainty Alignment in Large Language Models

Computer Science > Cryptography and Security [Submitted on 21 Apr 2026] Sensitivity Uncertainty Alignment in Large Language Models Prakul Sunil Hiremath, Harshit R. Hiremath We propose Sensitivity-Uncertainty Alignment (SUA), a framework for analyzing failures of large language models under adversarial and ambiguous inputs. We argue that adversarial sensitivity and ambiguity reflect a common issue: misalignment between prediction instability and model uncertainty. A reliable model should express higher uncertainty when its predictions are unstable; failure to do so leads to miscalibration. We define a scalar score, SUA_theta(x), capturing the difference between distributional sensitivity and predictive entropy. We show that minimizing its positive part bounds worst-case perturbed risk and relates to calibration error. We also formalize ambiguity collapse, where models produce overconfident outputs despite multiple valid interpretations. We introduce SUA-TR, a training method combining consistency regularization and entropy alignment, along with an abstention rule for safer inference. Across tasks including question answering and classification, SUA better identifies model failures than entropy or self-consistency alone. The framework is model-agnostic and provides a basis for improving reliability in evolving language models. Comments: 24 pages, 4 tables, 2 figures Subjects: Cryptography and Security (cs.CR) ACM classes: I.2.6; I.2.4; K.6.5 Cite as: arXiv:2604.20903 [cs.CR]   (or arXiv:2604.20903v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.20903 Focus to learn more Submission history From: Prakul Hiremath [view email] [v1] Tue, 21 Apr 2026 17:53:12 UTC (144 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)