Metraipolis › archive › dc_9161cab02f00
HybridRAG-BN: A Retrieval-Augmented Framework with Fine-Tuned Verification for Bangla KBQA — arXiv:2608.13004
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.13004
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:24:33.244Z
- SHA-256 of the archived text
b4fe113865e8eed0a12c2764d5d041f1d004bb15763e9419e2cf5b8474824f77- Stable URL of this page
https://metraipolis.com/documento/dc_9161cab02f00
How to cite
HybridRAG-BN: A Retrieval-Augmented Framework with Fine-Tuned Verification for Bangla KBQA — arXiv:2608.13004 — arXiv (en), https://arxiv.org/abs/2608.13004 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9161cab02f00 (Metraipolis archive dc_9161cab02f00, sha256 b4fe113865e8eed0a12c2764d5d041f1d004bb15763e9419e2cf5b8474824f77)
BibTeX
@misc{dc9161cab02f00,
title = {HybridRAG-BN: A Retrieval-Augmented Framework with Fine-Tuned Verification for Bangla KBQA — arXiv:2608.13004},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.13004},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9161cab02f00; sha256 b4fe113865e8eed0a12c2764d5d041f1d004bb15763e9419e2cf5b8474824f77},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13004. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Knowledge-base question answering (KBQA) systems rely on effective retrieval and reasoning mechanisms to generate accurate answers from external knowledge sources. However, developing reliable KBQA systems for low-resource languages such as Bangla remains challenging due to limited retrieval-focused research, scarce language resources, and difficulties in grounding generated responses in external knowledge. In this work, we propose HybridRAG-BN, a retrieval-augmented framework for Bangla KBQA that integrates hybrid retrieval using BM25 and BGE-M3, answer generation using the GGUF version of Gemma-4-31B-Instruct, and a LoRA-fine-tuned Gemma-4-31B-Instruct model for answer verification and refinement. To further improve robustness, the framework incorporates a post-processing stage that addresses unresolved cases through fallback answer replacement and DuckDuckGo-assisted retrieval. Experimental results demonstrate the effectiveness of the proposed framework, achieving token-level F1 scores of 0.71654 and 0.72912 on the public and private leaderboards, respectively, securing first place in the competition. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2608.13004 — 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 2026-10-19T04:17:42.389Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).