English(EN) When Should LLMs Abstain? Chain-of-Self-Questioning for Selective Risk Control

新的CoSQ框架通过评估事实支持来提高LLM的可靠性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-16 04:00

研究人员开发了一个名为链式自问（Chain-of-Self-Questioning, CoSQ）的新框架，以提高大语言模型的可靠性。CoSQ会提示模型在给出答案前评估其事实支持，从而在信息薄弱时允许模型弃权。在TruthfulQA数据集上的评估显示，与标准的链式思考提示相比，Grounded-CoSQ将错误承诺减少了32.1%，同时提高了答案的准确性。 AI

影响通过实现可调的回答或弃权决策来增强LLM的可靠性，这对于需要高事实准确性的应用至关重要。

排序理由介绍LLM安全新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 14 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 介绍LLM安全新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Ali \c{S}enol · 2026-09-16 04:00

何时应让大型语言模型（LLM）回避？链式自问以实现选择性风险控制

arXiv:2609.17516v1 Announce Type: cross Abstract: 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 assessmen…

本文如何被排名

报道来源 [1]

何时应让大型语言模型（LLM）回避？链式自问以实现选择性风险控制

相关实体

相关话题