跳到正文
返回论文列表
cs.MA提交于 已译

SCOPE:来源可信度与媒体机构画像引擎

SCOPE: Source Credibility and Outlet Profiling Engine

Ilyas Nagiyev · Miras Baisbay · Daniil Orel · Preslav Nakov

中文摘要

SCOPE 是一个用于评估新闻媒体机构偏见、事实性和可信度的多智能体系统。给定媒体 URL,系统协调专门智能体执行文章获取、内容分析、外部证据搜索、评分及报告生成。该方法遵循 MBFC 风格流程,并通过结构化演示界面使中间证据和智能体输出可检查。在包含 200 个媒体机构的基准测试中,SCOPE 在大多数指标上优于仅使用 LLM、仅文章、仅搜索及媒体背景调查的基线模型,实现了最低的偏见和事实性 MAE,100% 的失败事实核查检测率,以及最低的事实错误率。结果表明,分解的、基于证据的智能体工作流有助于支持更透明可靠的媒体画像。代码与演示已公开。

关键要点

  1. 01提出 SCOPE 多智能体系统,用于自动化评估新闻媒体的偏见、事实性与可信度。
  2. 02系统协调多个专门智能体,执行从文章获取到报告生成的完整分析流程。
  3. 03在 200 个媒体基准上,SCOPE 在偏见和事实性 MAE 等指标上优于多种基线。
  4. 04实现 100% 的失败事实核查检测率,并达到最低的事实错误率。
  5. 05通过结构化界面展示中间证据,提升了媒体画像过程的透明度与可解释性。

解读

尚无解读。

原始英文摘要

arXiv:2610.35929v1 Announce Type: cross Abstract: We present SCOPE, a multi-agent system for profiling news media outlets with respect to bias, factuality, and credibility. Given an outlet URL, SCOPE coordinates specialized agents for article acquisition, content analysis, external evidence search, scoring, and report generation. The system follows an MBFC-style methodology while making intermediate evidence and agent outputs inspectable through a structured demonstration interface. On a benchmark of 200 media outlets, SCOPE outperforms LLM-only, article-only, search-only, and media-background-check baselines on most metrics, achieving the lowest bias and factuality MAE, perfect failed-fact-check detection, and the lowest factual error rate. These results suggest that decomposed, evidence-grounded agent workflows can support more transparent and reliable media profiling. Our code is available at https://github.com/mbaisbay/SCOPE, and a live demonstration at https://scope-demo.streamlit.app/.

同方向论文 · cs.MA

查看全部 →

反向发现 · 这篇论文相关的工具与提示词

去交叉发现 →

关联提示词 · 6

智能体github.com/f/awesome-chatgpt-prompts·外部收录·

Weekend Planner

- Read the weekend weather, calendar and budget. - Find local events, hikes, exhibitions and restaurants. - Propose 3 plans: adventure, cozy, social, with times and costs. - Prepare reservation steps; book nothing without approval. - Rememb…

智能体github.com/f/awesome-chatgpt-prompts·外部收录·

Task Planner

--- name: sa-plan description: Structured Autonomy Planning Prompt model: Claude Sonnet 4.5 (copilot) agent: agent --- You are a Project Planning Agent that collaborates with users to design development plans. A development plan defines a…

研究github.com/f/awesome-chatgpt-prompts·外部收录·

Unified Research and Source Analysis Prompt

Unified, High-Precision Research & Analysis Prompt for ChatGPT and Perplexity AI ROLE & BEHAVIOR You are a professional researcher-analyst. Handle inputs as follows: * If the input is a URL/URI: open it fully with your browsing tool (e.g.…

智能体github.com/f/awesome-chatgpt-prompts·外部收录·

hermes agent desktop default system prompt

You are Hermes Agent, an intelligent AI assistant created by Nous Research. You are helpful, knowledgeable, and direct. You assist users with a wide range of tasks including answering questions, writing and editing code, analyzing informati…