Pareto Optimal Re-ranking with Semi-Automated Content Credibility Detection

  • 类型：arxiv
  • 标识：2606.18031
  • 链接：http://arxiv.org/abs/2606.18031v1
  • 主分类：risk
  • 形态：method
  • 被引：0
  • 被引来源：Semantic Scholar + OpenAlex
  • S2被引：0
  • OpenAlex被引：0
  • 影响力被引：0
  • TLDR：An optimization-based method to improve the credibility of news content on social media feeds by refining existing content rankings is presented and a robust semi-automated pipeline for assigning credibility scores to content based on a mixture of retrieval-augmented score assignments and human-generated fact-checks is proposed.
  • OpenAlex ID：W7165017255
  • OpenAlex DOI：10.48550/arxiv.2606.18031
  • DOI：10.48550/arxiv.2606.18031
  • DOI来源：OpenAlex
  • 开放获取：green
  • 开放获取链接：https://doi.org/10.48550/arxiv.2606.18031
  • OpenAlex更新：2026-07-19
  • 待LLM分类：否
  • 成熟度：research
  • 场景：content credibility、news re-ranking、misinformation
  • 标题中文：基于半自动化内容可信度检测的帕累托最优重排序
  • TLDR中文：提出一种基于优化的方法，通过精炼现有内容排序来提升社交媒体信息流中新闻内容的可信度；同时构建一条鲁棒的半自动化流水线，基于检索增强打分与人工事实核查的混合方式为内容赋予可信度分数。
  • 来源文件：
  • /inbox/tom/_candidates/2026-06-17-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]