@inproceedings{rahman-etal-2026-vlce,
    title = "{VLCE}: A Knowledge-Enhanced Framework for Image Description in Disaster Assessment",
    author = "Rahman, Md. Mahfuzur  and
      Kamal, Marufa  and
      Rahman, Fahad  and
      Siddique, Sunzida  and
      Hasan, Ahmed Rafi  and
      Haque, Mohd Ariful  and
      Gupta, Kishor Datta  and
      George, Roy",
    editor = "Yan, Qianqi  and
      Montariol, Syrielle  and
      Fan, Yue  and
      Gu, Jing  and
      Pan, Jiayi  and
      Li, Manling  and
      Kordjamshidi, Parisa  and
      Suhr, Alane  and
      Wang, Xin Eric",
    booktitle = "Proceedings of the 4th Workshop on Advances in Language and Vision Research ({ALVR})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.alvr-main.15/",
    pages = "186--198",
    ISBN = "979-8-89176-398-2",
    abstract = "General-purpose vision-language models (VLMs) such as LLaVA and QwenVL produce descriptions of disaster imagery that lack domain-specific vocabulary and actionable detail. We propose the Vision-Language Caption Enhancer (), a framework that integrates external semantic knowledge from ConceptNet and WordNet into the caption generation process for post-disaster satellite and UAV imagery. operates in two stages: first, a baseline VLM generates an initial caption conditioned on YOLOv8 object detections; second, a knowledge-enriched sequential model, a CNN-LSTM or a hierarchical cross-modal Transformer, refines the caption using a vocabulary augmented with 1,566 domain-relevant terms extracted from knowledge graphs. We evaluate on two disaster benchmarks: xBD (satellite, 6,369 images, 3 damage classes) and RescueNet (UAV, 4,494 images, 12 damage classes), using CLIPScore for semantic alignment and InfoMetIC for informativeness. On RescueNet with the Transformer decoder, with knowledge graph enrichment produces captions preferred over QwenVL baselines in 95.33{\%} of image pairs on InfoMetIC and 73.64{\%} on CLIPScore. Qualitative analysis shows that without knowledge graph integration, generated captions exhibit hallucinations, word repetition, and semantic incoherence, whereas knowledge-enriched captions maintain factual consistency and domain-appropriate vocabulary. intended as a continuous, extensible monitor of differential framing under changing real-world inputs."
}