跳到正文
arXiv cs.AI· Quy P. Nguyen, Duong Q. Nguyen, Dinh P. T. Nguyen, Truong-Giang T. Le, Truong A. Bui, Vi H. Vo, Quang-Thinh Bui, My-Phuong Ngo, Trong N. Do, Thao P. Le, Phuc M. Nguyen, H. Nguyen-Xuan·· 10 小时前AI 评分31

VeriMath:面向课程对齐数学测评题的人机协同生成与验证框架

VeriMath: Human-in-the-Loop Generation and Verification of Curriculum-Aligned Mathematics Assessment Items

AI 导读

VeriMath 是一个人机协同框架,用于生成受课程约束的数学测评题草稿,先锚定考试题型与认知层级,再经自动验证与引导修复后交由专家审核。在越南 12 年级课程案例中,使用 4,555 道数学题和 50 项生成要求测试,两种模型骨干下每轮有 94%(47/50)的要求产出通过验证器的草稿,盲评专家严格判定最多 56.8% 的生成题目达到教师可用标准。

正文 · 原文

Authors:Quy P. Nguyen, Duong Q. Nguyen, Dinh P. T. Nguyen, Truong-Giang T. Le, Truong A. Bui, Vi H. Vo, Quang-Thinh Bui, My-Phuong Ngo, Trong N. Do, Thao P. Le, Phuc M. Nguyen, H. Nguyen-Xuan

View PDF HTML (experimental)

Abstract:Automatic generation of mathematics assessment items is a growing area in educational artificial intelligence, yet classroom deployment remains challenging. Generated questions must satisfy multiple constraints: mathematical correctness, curriculum alignment, appropriate cognitive difficulty, and educator reviewability. While prior work has advanced text generation, reliable assessment authoring requires granular control over localized examination formats and expert educational judgment. To address this challenge, we present VeriMath, a generalized, human-in-the-loop framework for generating rigorous, curriculum-constrained mathematics assessment drafts. Using annotated reference items, the framework anchors generation to the requested examination section and cognitive reasoning level, then applies sequential automated verification and guided repair before submitting drafts for expert review. We evaluate VeriMath through a national curriculum case study using 4,555 mathematics items from the Vietnamese Grade 12 curriculum and 50 distinct generation requirements covering multiple-choice, true/false, and short-answer formats. Across two model backbones, the framework produces verifier-accepted drafts for 94% (47/50) of requirements per run. Blind expert evaluations confirm high mathematical accuracy and curriculum alignment, with strict teacher-readiness assessments accepting up to 56.8% of generated items. Analysis of rejected drafts reveals persistent domain-agnostic challenges involving formatting, statement validity, and solution-step completeness. These findings demonstrate that VeriMath can bridge generative AI and dependable educational applications by producing highly reviewable assessment drafts within tightly constrained national curriculum frameworks.
Subjects: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
Cite as: arXiv:2611.23456 [cs.AI]
  (or arXiv:2611.23456v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.23456

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Duong Nguyen Quoc [view email]
[v1] Tue, 17 Nov 2026 20:05:23 UTC (451 KB)

来源:arXiv cs.AI · arxiv.org