English(EN) Authority Bias in Conversational Search Engines for Academic Paper Recommendation

研究发现大型语言模型在学术论文推荐中表现出显著的权威性偏见

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-02 04:00

一项新近发表在arXiv上的研究调查了大型语言模型（LLMs）在用于学术论文推荐时出现的“权威性偏见”现象。研究人员发现，大型语言模型倾向于根据作者声望、发表地点和引用次数来推荐论文，而非论文的实际内容。这种偏见被认为是显著的，并且在不同的LLMs之间存在差异，仅通过提示层面的去偏技术只能部分缓解。研究还强调了一个“说做差距”，即去偏指令在压制权威性提及方面比纠正潜在推荐偏见更有效，这表明行为偏见被表面审计低估了。 AI

影响凸显了大型语言模型可能加剧现有学术不平等的风险，需要进行仔细的审计和去偏。

排序理由关于大型语言模型行为新发现的学术论文。[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: 28 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于大型语言模型行为新发现的学术论文。[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) · Uthman Jinadu, Parsa Ghazvinian, Anjila Budathoki, Benjamin M. Ampel, Rajshekhar Sunderraman, Yi Ding · 2026-09-02 04:00

对话式搜索引擎在学术论文推荐中的权威偏见

arXiv:2609.00248v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used as conversational search engines for academic literature, yet whether they judge papers on content or on authority signals has not been tested causally. We investigate authority bia…

本文如何被排名

报道来源 [1]

对话式搜索引擎在学术论文推荐中的权威偏见

相关实体

相关话题