English(EN) AI models often give the right answers but point to the wrong sources

AI模型出现引文幻觉，新基准测试揭示

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-25 07:30

包括GPT和Gemini在内的领先AI模型经常提供正确答案，但引用不存在或不相关的证据。北京大学的研究人员将这种现象称为“引文幻觉”，它在法律和医学等关键领域构成了重大风险。为解决这一问题，开发了一个名为CiteVQA的新基准测试，以系统地评估和识别这些引文错误。 AI

影响新的基准测试CiteVQA突出了AI模型的引文幻觉问题，对受监管行业构成风险，并促使开发更可靠的引文方法。

排序理由该集群描述了一个用于评估AI模型行为的新学术基准测试。 [lever_c_demoted from research: ic=1 ai=1.0]

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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一个用于评估AI模型行为的新学术基准测试。 [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: 137 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

The Decoder TIER_1 English(EN) · Jonathan Kemper · 2026-05-25 07:30

AI模型常给出正确答案但指向错误来源

<p><img alt="Graphic: AI tool highlights text passages in a PDF to identify errors and incorrect information." class="attachment-full size-full wp-post-image" height="1047" src="https://the-decoder.com/wp-content/uploads/2026/05/CiteVQA-Spot-Error-PDF-Hallucination-Nano-Banana-Pr…