Metraipolis › archive › dc_6bc7aa266fc5

BIT.UA at BioASQ 14B: Modular Retrieval with pg_textsearch and Qdrant, and Agent-Based Answer Generation — arXiv:2609.04999

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04999
License (as archived)
CC0-1.0
Archived
2026-10-16T22:35:21.098Z
SHA-256 of the archived text
6501127d8ae9d1ed5b36154b8606a54a2ebb55bb0526e180c1ddaa0dcdfbe4bb
Stable URL of this page
https://metraipolis.com/documento/dc_6bc7aa266fc5

How to cite

BIT.UA at BioASQ 14B: Modular Retrieval with pg_textsearch and Qdrant, and Agent-Based Answer Generation — arXiv:2609.04999 — arXiv (en), https://arxiv.org/abs/2609.04999 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6bc7aa266fc5 (Metraipolis archive dc_6bc7aa266fc5, sha256 6501127d8ae9d1ed5b36154b8606a54a2ebb55bb0526e180c1ddaa0dcdfbe4bb)
BibTeX
@misc{dc6bc7aa266fc5,
  title = {BIT.UA at BioASQ 14B: Modular Retrieval with pg_textsearch and Qdrant, and Agent-Based Answer Generation — arXiv:2609.04999},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04999},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6bc7aa266fc5; sha256 6501127d8ae9d1ed5b36154b8606a54a2ebb55bb0526e180c1ddaa0dcdfbe4bb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04999. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper describes the participation of the this http URL team from the University of Aveiro in the 14th edition of the BioASQ Task B challenge on biomedical question answering. Building on our previous submissions, we introduced a substantially refactored and modular codebase, and made significant changes to both the retrieval and generation components of the pipeline. For Phase~A document retrieval, we replaced the PyTerrier PISA index with PostgreSQL-based pg\_textsearch for BM25 retrieval and adopted Qdrant for dense embedding indexing, enabling more efficient storage and GPU-accelerated similarity search. We explored HyDE-based query expansion alongside a Context-1 retrieval strategy. A new reranker training pipeline was developed, incorporating dense retrieval for negative sampling. For Phases A+ and B answer generation, we introduced an LLM-as-a-judge framework and a novel agent quorum mechanism, where multiple agents with diverse prompts debate and iteratively converge on a consensus answer using adaptive document retention. We also participated in the snippets generation subtask for the first time. Our systems achieved competitive results across all batches, with Phase~A systems achieving MAP ranks of 5 (Batch~1,3). We discuss the impact of these architectural changes, lessons learned, and outline directions for future work including SPLADE and ColBERT integration. All code is openly available: this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.04999 — 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 2026-10-16T22:21:16.289Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).