Learning When Not to Decide: A Framework for Overcoming Factual Presumptuousness in AI Adjudication

Computer Science > Artificial Intelligence [Submitted on 21 Apr 2026] Learning When Not to Decide: A Framework for Overcoming Factual Presumptuousness in AI Adjudication Mohamed Afane, Emily Robitschek, Derek Ouyang, Daniel E. Ho A well-known limitation of AI systems is presumptuousness: the tendency of AI systems to provide confident answers when information may be lacking. This challenge is particularly acute in legal applications, where a core task for attorneys, judges, and administrators is to determine whether evidence is sufficient to reach a conclusion. We study this problem in the important setting of unemployment insurance adjudication, which has seen rapid integration of AI systems and where the question of additional fact-finding poses the most significant bottleneck for a system that affects millions of applicants annually. First, through a collaboration with the Colorado Department of Labor and Employment, we secure rare access to official training materials and guidance to design a novel benchmark that systematically varies in information completeness. Second, we evaluate four leading AI platforms and show that standard RAG-based approaches achieve an average of only 15% accuracy when information is insufficient. Third, advanced prompting methods improve accuracy on inconclusive cases but over-correct, withholding decisions even on clear cases. Fourth, we introduce a structured framework requiring explicit identification of missing information before any determination (SPEC, Structured Prompting for Evidence Checklists). SPEC achieves 89% overall accuracy, while appropriately deferring when evidence is insufficient -- demonstrating that presumptuousness in legal AI is systematic but addressable, and that doing so is a necessary step towards systems that reliably support, rather than supplant, human judgment wherever decisions must await sufficient evidence. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2604.19895 [cs.AI]   (or arXiv:2604.19895v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.19895 Focus to learn more Submission history From: Mohamed Afane [view email] [v1] Tue, 21 Apr 2026 18:17:08 UTC (3,743 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < 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?)