Metraipolis › archive › dc_af7930ea355d

BengaliMCQ: Automatic Generation and Answer Prediction of Academic Multiple-Choice Questions in a Low-Resource Language — arXiv:2608.15547

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.15547
License (as archived): CC0-1.0
Archived: 2026-10-18T18:58:45.573Z
SHA-256 of the archived text: 3d3a1cc410766fd8fccab9c5fda2f118350f73c1a8693a31923f895c4a155c0a
Stable URL of this page: https://metraipolis.com/documento/dc_af7930ea355d

How to cite

BengaliMCQ: Automatic Generation and Answer Prediction of Academic Multiple-Choice Questions in a Low-Resource Language — arXiv:2608.15547 — arXiv (en), https://arxiv.org/abs/2608.15547 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_af7930ea355d (Metraipolis archive dc_af7930ea355d, sha256 3d3a1cc410766fd8fccab9c5fda2f118350f73c1a8693a31923f895c4a155c0a)

BibTeX

@misc{dcaf7930ea355d,
  title = {BengaliMCQ: Automatic Generation and Answer Prediction of Academic Multiple-Choice Questions in a Low-Resource Language — arXiv:2608.15547},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15547},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_af7930ea355d; sha256 3d3a1cc410766fd8fccab9c5fda2f118350f73c1a8693a31923f895c4a155c0a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15547. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Traditional retrieval-augmented generation (RAG) frameworks process documents without attending to their hierarchical structure, leading to poor performance, especially in low-resource languages such as Bengali. To address this, we propose a structure-aware RAG framework that models Bengali textbooks as hierarchical graphs and uses a contrastively trained graph neural network to retrieve a small set of relevant passages. These passages provide focused context for a large language model, enabling topic-specific multiple-choice question (MCQ) generation and in-domain answer prediction. Experimental results demonstrate that our framework outperforms strong dense retrieval baselines across retrieval metrics, produces more relevant MCQs, and achieves superior answer prediction accuracy.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.15547 — 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 2026-10-18T18:06:57.858Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).