Towards reliable multimodal disaster severity assessment through preference optimization and explainable vision-language reasoning

The paper introduces a two‑stage training framework that combines Supervised Fine‑Tuning (SFT) and Direct Preference Optimization (DPO) to improve multimodal disaster severity assessment. It creates two datasets—ReasoningSet for validated rationales and PreferenceSet for paired rationales—using a single Human‑in‑the‑Loop workflow. Experiments on InternVL‑3‑8B and LLaVA‑1.5‑7B show that SFT boosts classification accuracy and Macro‑F1, while DPO further enhances interpretability and alignment with human judgment.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• reinforcement-learning
• fine-tuning
• multimodal
• safety