mlsanityData to 7 Oct 2026

Reducing Hallucinations: Enhancing VQA for Flood Disaster Damage Assessment with Visual Contexts

arXiv 2312.13848 ↗First posted 21 Dec 2023cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

The zero-shot performance of visual question answering (VQA) models relies heavily on prompts. For example, a zero-shot VQA for disaster scenarios could leverage well-designed Chain of Thought (CoT) prompts to stimulate the model's potential. However, using CoT prompts has some problems, such as causing an incorrect answer in the end due to the hallucination in the thought process. In this paper, we propose a zero-shot VQA named Flood Disaster VQA with Two-Stage Prompt (VQA-TSP). The model generates the thought process in the first stage and then uses the thought process to generate the final answer in the second stage. In particular, visual context is added in the second stage to relieve the hallucination problem that exists in the thought process. Experimental results show that our method exceeds the performance of state-of-the-art zero-shot VQA models for flood disaster scenarios in total. Our study provides a research basis for improving the performance of CoT-based zero-shot VQA.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 8 of its 12 references that are in the map. First posted on arXiv 21 Dec 2023.

Builds on

8 of 12 references.

References · 8

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  3. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  4. 2023Multimodal Chain-of-Thought Reasoning in Language Modelscited by 740
  5. 2020RSVQA: Visual Question Answering for Remote Sensing Datacited by 197
  6. 2022Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Trainingcited by 88
  7. 2023Self-prompted Chain-of-Thought on Large Language Models for Open-domain Multi-hop Reasoningcited by 21
  8. 2023Unleashing the Potential of Large Language Model: Zero-shot VQA for Flood Disaster Scenariocited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026DisasterVQA: A Visual Question Answering Benchmark Dataset for Disaster Scenescited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025ZeShot-VQA: Zero-Shot Visual Question Answering Framework with Answer Mapping for Natural Disaster Damage Assessment
  2. 2023Exploring Question Decomposition for Zero-Shot VQA
  3. 2025Think First, Assign Next (ThiFAN-VQA): A Two-stage Chain-of-Thought Framework for Post-Disaster Damage Assessment
  4. 2023Improving Zero-shot Visual Question Answering via Large Language Models with Reasoning Question Prompts
  5. 2025FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA
  6. 2026Instruct-ICL: Instruction-Guided In-Context Learning for Post-Disaster Damage Assessment
  7. 2025The Quest for Visual Understanding: A Journey Through the Evolution of Visual Question Answering
  8. 2023Investigating Prompting Techniques for Zero- and Few-Shot Visual Question Answering