用于教育教科书历史偏见检测的代理评估架构
An Agentic Evaluation Architecture for Historical Bias Detection in Educational Textbooks
AI总结：
本文提出一种代理评估架构，通过多模态筛查代理、异质陪审团和元代理，有效检测教育教科书中的隐性偏见，实验表明其在经济性和准确性上具有优势。
摘要：
历史教科书常常包含隐性偏见、民族主义叙述和选择性遗漏，这些在大规模审计中难以检测。我们提出了一种代理评估架构，包括一个多模态筛查代理、一个由五个评估代理组成的异质陪审团以及一个用于综合裁决和人类升级的元代理。核心贡献是源归属协议，该协议区分教科书叙述与引用的历史来源，防止因单模型评估器导致的系统性误报。在一项针对罗马尼亚高中历史教科书的实证研究中，270个被筛查的片段中有83.3%被分类为教学上可接受（平均严重性2.9/7），而零样本基线为5.4/7，证明了代理 deliberation 减少了过度惩罚。在盲人人类评估（18名评估者，54次比较）中，独立 deliberation 配置在64.8%的情况下优于启发式变种和零样本基线。每本教科书约2美元的成本使代理评估架构成为教育治理中的经济可行决策支持工具。
英文摘要：
History textbooks often contain implicit biases, nationalist framing, and selective omissions that are difficult to audit at scale. We propose an agentic evaluation architecture comprising a multimodal screening agent, a heterogeneous jury of five evaluative agents, and a meta-agent for verdict synthesis and human escalation. A central contribution is a Source Attribution Protocol that distinguishes textbook narrative from quoted historical sources, preventing the misattribution that causes systematic false positives in single-model evaluators. In an empirical study on Romanian upper-secondary history textbooks, 83.3\% of 270 screened excerpts were classified as pedagogically acceptable (mean severity 2.9/7), versus 5.4/7 under a zero-shot baseline, demonstrating that agentic deliberation mitigates over-penalization. In a blind human evaluation (18 evaluators, 54 comparisons), the Independent Deliberation configuration was preferred in 64.8\% of cases over both a heuristic variant and the zero-shot baseline. At approximately \$2 per textbook, these results position agentic evaluation architectures as economically viable decision-support tools for educational governance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
