PulseAugur
中
实时 11:10:15
English(EN) Eroding the Truth-Default: A Causal Analysis of Human Susceptibility to Foundation Model Hallucinations and Disinformation in the Wild

新框架揭示人类易受人工智能幻觉影响

一项新的研究论文介绍了JudgeGPT和RogueGPT,这是一个旨在调查人类如何容易受到基础模型幻觉和虚假信息影响的框架。该研究分析了包括GPT-4和Llama 2在内的五个基础模型的918项评估,发现政治取向对检测准确率的影响很小。相反,熟悉“假新闻”成为一个重要因素,这表明接触可以作为人类辨别能力的对抗性训练的一种形式。该研究强调了一个“流畅性陷阱”,即像GPT-4这样的模型的高度流畅输出与人类文本无法区分,从而损害了信息源监控机制。 AI

影响 强调了对人工智能生成虚假信息的认知脆弱性,并为“预先揭穿”干预措施提出了新方法。

排序理由 学术论文,详细介绍了新框架以及对人类易受人工智能幻觉影响的分析。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

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

新框架揭示人类易受人工智能幻觉影响

本文如何被排名

Signal score
1 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
学术论文,详细介绍了新框架以及对人类易受人工智能幻觉影响的分析。[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
1 days old
Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.CL TIER_1 English(EN) · Alexander Loth, Martin Kappes, Marc-Oliver Pahl ·

    Eroding the Truth-Default: A Causal Analysis of Human Susceptibility to Foundation Model Hallucinations and Disinformation in the Wild

    arXiv:2601.22871v3 Announce Type: replace-cross Abstract: As foundation models (FMs) approach human-level fluency, distinguishing synthetic from organic content has become a key challenge for Trustworthy Web Intelligence. This paper presents JudgeGPT and RogueGPT, a dual-axis fra…