An Agentic Evaluation Architecture for Historical Bias Detection in Educational Textbooks

arXiv:2604.07883v1 Announce Type: cross Abstract: 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.

Related

• Self-Debias: Self-correcting for Debiasing Large Language Models
• Learning Who Disagrees: Demographic Importance Weighting for Modeling Annotator Distributions with DiADEM
• From Ground Truth to Measurement: A Statistical Framework for Human Labeling
• Evaluating LLMs for Demographic-Targeted Social Bias Detection: A Comprehensive Benchmark Study
• Seeing Like an AI: How LLMs Apply (and Misapply) Wikipedia Neutrality Norms

Source: arXiv cs.CL | 2026-04-10