发表机构
North South University（南北大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
PhysicsMate是首个基于NCTB课程的中学物理孟加拉语问答基准，通过低秩适配显著提升小模型闭卷准确率，并量化出可离线运行的4B模型。
AI 中文摘要
孟加拉语中学教育缺乏基于课程的STEM问题求解基准，通用语言模型在处理物理问题所需的精确术语、单位约定和推导方面存在困难。我们引入了PhysicsMate，这是一个包含1834个问答对的基准，基于国家课程与教材委员会（NCTB）九年级至十年级物理教学大纲构建，并锚定在一个包含1760个节点和2600条边、跨越十种本体类型的关系知识图谱上。我们采用统一配方，在0.6B、1.7B和4B参数规模下进行低秩适配，并展示了在所有规模下闭卷准确率的显著提升（分别提高+5.5、+15.0和+23.3个百分点）。节点类型分析表明，适配受益最大的是结构化课程知识，即物理量和命名定律，而受益最小的是松散指定的实体级知识。4B模型已被适配并量化成一个小的离线二进制文件，可在资源受限环境中用于本地推理，为连接性和硬件受限环境中的课程对齐物理支持提供了一条可行路径。
英文摘要
Bengali secondary education lacks curriculum-grounded benchmarks for STEM question-solving, and general-purpose language models struggle with the precise terminology, unit conventions, and derivations that physics problems demand. We introduce PhysicsMate, a benchmark of 1834 question-answer pairs built from the National Curriculum and Textbook Board (NCTB) Grade 9-10 physics syllabus and grounded in a multi-relational knowledge graph of 1760 nodes and 2600 edges across ten ontological types. We Low-Rank Adapt at 0.6B, 1.7B, and 4B parameters, with a unified recipe and demonstrate a significant increase in closed-book accuracy in all scales (+5.5, +15.0, and +23.3 percentage points). A node-type analysis shows that the most benefited by adaptation is the structured curricular knowledge, which consists of physical quantities and named laws, while the least benefited is the loosely specified entity-level knowledge. The 4B model has been adapted and quantized to a small offline binary that can be used for local inference in resource constrained environments and offers a viable path to curriculum aligned physics support in environments with limited connectivity and hardware.
Comments6 pages, 3 figures, 5 tables. Accepted at 11th IEEE Asia-Pacific Conference on Computer Science and Data Engineering (IEEE CSDE 2026)
