Metraipolis › archive › dc_ecfef43e4bbf

RE-SciVQA: Improving Scientific VQA With Context-Relevant Retrieval and Lightweight MLLM Adaptation — arXiv:2611.00242

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.00242
License (as archived): CC0-1.0
Archived: 2026-11-03T10:21:40.315Z
SHA-256 of the archived text: 724d6db76265d7795852ca5de840b56ca648a6c29beccbfacc0186960c269cf4
Stable URL of this page: https://metraipolis.com/documento/dc_ecfef43e4bbf

How to cite

RE-SciVQA: Improving Scientific VQA With Context-Relevant Retrieval and Lightweight MLLM Adaptation — arXiv:2611.00242 — arXiv (en), https://arxiv.org/abs/2611.00242 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ecfef43e4bbf (Metraipolis archive dc_ecfef43e4bbf, sha256 724d6db76265d7795852ca5de840b56ca648a6c29beccbfacc0186960c269cf4)

BibTeX

@misc{dcecfef43e4bbf,
  title = {RE-SciVQA: Improving Scientific VQA With Context-Relevant Retrieval and Lightweight MLLM Adaptation — arXiv:2611.00242},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00242},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ecfef43e4bbf; sha256 724d6db76265d7795852ca5de840b56ca648a6c29beccbfacc0186960c269cf4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00242. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A deep understanding of scientific literature often relies on interpreting figures that contain key information beyond the main text. Leveraging Large Language Models (LLMs) to extract insights from these figures can significantly accelerate knowledge discovery. Existing works on Scientific Visual Question Answering rely on resource-intensive training pipelines that are often inaccessible and require large computational resources. Instead of designing complex architectures, we propose RE- SciVQA, which focuses on improving the quality of retrieved context and fine-tuning small LLMs with parameter-efficient LoRA training. Using a simple query expansion step, relevant section headers are appended to the original question to improve the retrieval coverage. In addition, a simple adjustment of similarity scores is applied using figure references and caption alignment. On the SciVQA benchmark, RE-SciVQA achieves a ROUGE-1 F1 score of 73.9%, outperforming chart-focused models such as UniChart (14.7%), ChartGemma (6.9%), and Matcha-ChartQA (6.3%). Our relevance-enhanced RAG setup also improves the exact match by 11.9% and the fuzzy match by 29.5% compared with a standard RAG baseline, resulting in an overall gain of 14.3%. We also examine closed-ended infinite visual questions, a category in which chart-understanding models often struggle. Our experiments show that using plot digitization instead of synthetic captions leads to an 18.5% improvement for this question type.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.00242 — 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 2026-11-03T10:19:49.743Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).