{
  "id": 7698702,
  "title": "When Should LLMs Abstain? Chain-of-Self-Questioning for Selective Risk Control",
  "url": "https://urgent.news/2026/09/15/when-should-llms-abstain-chain-of-self-questioning-for-selective-risk",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-15T17:52:24.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.17516v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "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…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}