English(EN) Same Verdict, Different Readers: Personalizing Fact-Checking Explanations from Relative Preferences

新框架为读者个性化事实核查解释

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-28 04:00

研究人员开发了一个名为 PERPL 的新框架，用于个性化在线读者的事实核查解释。该系统在确保事实准确性的同时，将现有解释调整为符合个人偏好。PERPL 解决了区分读者特定偏好与一般质量以及超越预定义风格的学习等挑战。实验表明，PERPL 在个性化匹配度和事实保真度方面优于大型语言模型。 AI

影响通过根据个人需求定制解释，可以提高用户对人工智能生成信息的信任度和理解度。

排序理由这是一篇研究论文，详细介绍了用于个性化事实核查解释的新框架。[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: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇研究论文，详细介绍了用于个性化事实核查解释的新框架。[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, product; 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。

arXiv cs.CL TIER_1 English(EN) · Haokun Wen, Xuemeng Song, Mong-Li Lee, Wynne Hsu · 2026-10-28 04:00

相同判决，不同读者：基于相对偏好个性化事实核查解释

arXiv:2610.37380v1 Announce Type: new Abstract: Fact-checking explanations help Web users understand why a claim receives its verdict, yet the same explanation may not satisfy readers with different backgrounds and preferences. We formulate Faithful Personalized Fact-Checking Exp…