PhysicsMate: A Curriculum-Grounded Bengali Benchmark for Secondary Physics QA with Small-Model Adaptation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 12 references that are in the map. First posted on arXiv 30 Sep 2026.
Builds on
11 of 12 references.
References · 11
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
- 2025Qwen3 Technical Reportcited by 8,195
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
- 2024LoRA Learns Less and Forgets Lesscited by 313
- 2021BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Banglacited by 123
- 2025BnMMLU: Measuring Massive Multitask Language Understanding in Bengalicited by 6
- 2024Paramanu: Compact and Competitive Monolingual Language Models for Low-Resource Morphologically Rich Indian Languagescited by 4
- 2024BEnQA: A Question Answering and Reasoning Benchmark for Bengali and Englishcited by 4
- 2024Knowledge Graphs are all you need: Leveraging KGs in Physics Question Answeringcited by 2
- 2025An Ontology for Representing Curriculum and Learning Materialcited by 2
Built on by
Not cited yet.