SOURCE-LINKED INTELLIGENCE

When Should LLMs Abstain? Chain-of-Self-Questioning for Selective Risk Control

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

Large language models can produce fluent answers when their factual support is weak. This paper introduces Chain-of-Self-Questioning (CoSQ), a prompt-only framework that makes answer commitment conditional on an explicit assessment of the information required to answer a question. We evaluate three CoSQ variants under seventeen conditions on the 817-item TruthfulQA multiple-choice validation set using eleven open-weight and hosted model families. In the final balanced-option protocol, Grounded-CoSQ at τ=0.90 reduces the mean unconditional wrong-commitment rate from 13.1% under chain-of-thought

Read original source ↗ Open in workspace

recordType

paper

region

Global