AI RESEARCH
Second Guess: Detecting Uncertainty Through Abstention and Answer Stability in Small Language Models
arXiv CS.AI
•
ArXi:2605.25394v1 Announce Type: new Large language models often generate confident but incorrect answers rather than abstaining when uncertain. This problem is particularly acute for small language models (SLMs), where computational constraints and autonomous operation amplify the need for reliable uncertainty detection. We propose _Second Guess_, a lightweight, parameter-free prompting technique for abstention in multiple-choice question answering (MCQA) that is well-suited for SLMs.