Bridging the Detection-to-Abstention Gap in Reasoning Models under Insufficient Information

ArXi:2605.28070v1 Announce Type: new We highlight a failure mode of large reasoning models on questions with insufficient information: models may recognize that a problem is under-specified, yet still continue reasoning and produce uned final answers instead of abstaining. We formalize this mismatch as the detection-to-abstention gap, where detected insufficiency fails to translate into final abstention. This gap is especially concerning in high-risk domains such as medical AI, where answers based on incomplete evidence can be harmful than refusal.