@inproceedings{bhat-etal-2025-expertneurons,
    title = "{E}xpert{N}eurons at {S}ci{VQA}-2025: Retrieval Augmented {VQA} with Vision Language Model ({RAVQA}-{VLM})",
    author = "Bhat, Nagaraj N  and
      Mondal, Joydeb  and
      Sarkar, Srijon",
    editor = "Ghosal, Tirthankar  and
      Mayr, Philipp  and
      Singh, Amanpreet  and
      Naik, Aakanksha  and
      Rehm, Georg  and
      Freitag, Dayne  and
      Li, Dan  and
      Schimmler, Sonja  and
      De Waard, Anita",
    booktitle = "Proceedings of the Fifth Workshop on Scholarly Document Processing (SDP 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/mtsummit-25-ingestion/2025.sdp-1.20/",
    doi = "10.18653/v1/2025.sdp-1.20",
    pages = "221--229",
    ISBN = "979-8-89176-265-7",
    abstract = "We introduce RAVQA-VLM, a novel Retrieval-Augmented Generation (RAG) architecture with Vision Language Model for the SciVQA challenge, which targets closed-ended visual and nonvisual questions over scientific figures drawn from ACL Anthology and arXiv papers (Borisova and Rehm, 2025). Our system first encodes each input figure and its accompanying metadata (caption, figure ID, type) into dense embed- dings, then retrieves context passages from the full PDF of the source paper via a Dense Passage Retriever (Karpukhin et al., 2020). The extracted contexts are concatenated with the question and passed to a vision-capable generative backbone (e.g., Phi-3.5, Pixtral-12B, Mixtral-24B-small, InterVL-3-14B) fine-tuned on the 15.1K SciVQA training examples (Yang et al., 2023; Pramanick et al., 2024). We jointly optimize retrieval and generation end-to-end to minimize answer loss and mitigate hallucinations (Lewis et al., 2020; Rujun Han and Castelli, 2024). On the SciVQA test set, RAVQA-VLM achieves significant improvements over parametric only baselines, with relative gains of +5{\%} ROUGE1 and +5{\%} ROUGE-L, demonstrating the efficacy of RAG for multimodal scientific QA."
}