English(EN) Well this is interesting. Only an unpublished masters dissertation, but from a good programme ( @[email protected] ) Hedwig Oldenhof's

研究发现大型语言模型可复制内隐和外显态度

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-14 13:04

乌得勒支大学一篇由 Hedwig Oldenhof 撰写的硕士论文表明，大型语言模型（LLMs）可以复制内隐和外显态度。研究表明，LLMs 表现出的偏见与人类内隐联想测试（IAT）和外显问卷中发现的偏见相似。 AI

影响表明大型语言模型可能内化并复制人类偏见，影响人工智能伦理和发展。

排序理由该集群报道了一项未发表的硕士论文的研究结果，这构成了学术研究。[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; 该集群报道了一项未发表的硕士论文的研究结果，这构成了学术研究。[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: 63 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。