Metraipolis › archive › dc_449fbce31cf2

PhysicsMate: A Curriculum-Grounded Bengali Benchmark for Secondary Physics QA with Small-Model Adaptation — arXiv:2610.00664

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.00664
License (as archived): CC0-1.0
Archived: 2026-10-06T13:54:12.881Z
SHA-256 of the archived text: 042cc1f716df8d765c8567fa2afa160c19b5cdc27fc8a9c1adc1ab46e4f08e58
Stable URL of this page: https://metraipolis.com/documento/dc_449fbce31cf2

How to cite

PhysicsMate: A Curriculum-Grounded Bengali Benchmark for Secondary Physics QA with Small-Model Adaptation — arXiv:2610.00664 — arXiv (en), https://arxiv.org/abs/2610.00664 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_449fbce31cf2 (Metraipolis archive dc_449fbce31cf2, sha256 042cc1f716df8d765c8567fa2afa160c19b5cdc27fc8a9c1adc1ab46e4f08e58)

BibTeX

@misc{dc449fbce31cf2,
  title = {PhysicsMate: A Curriculum-Grounded Bengali Benchmark for Secondary Physics QA with Small-Model Adaptation — arXiv:2610.00664},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00664},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_449fbce31cf2; sha256 042cc1f716df8d765c8567fa2afa160c19b5cdc27fc8a9c1adc1ab46e4f08e58},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00664. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.00664 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T12:15:34.633Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).