Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The authors introduce WeatherQA, a new multimodal reasoning benchmark for meteorology, and Logically Consistent Reinforcement Fine-Tuning (LoCo-RFT) to address the issue of self-contradictory reasoning in VLMs. LoCo-RFT incorporates a logical consistency reward to ensure the model's reasoning aligns with its final answer, crucial for high-stakes domains like meteorology. The resulting model, Weather-R1, achieves a 9.8 percentage point improvement over the baseline on WeatherQA, surpassing supervised fine-tuning, standard RFT, and even the original Qwen2.5-VL-32B.
VLMs can now reason more faithfully in high-stakes domains like meteorology, thanks to a novel reinforcement learning approach that penalizes self-contradictory reasoning.
While Vision Language Models (VLMs) show advancing reasoning capabilities, their application in meteorology is constrained by a domain gap and a reasoning faithfulness gap. Specifically, mainstream Reinforcement Fine-Tuning (RFT) can induce Self-Contradictory Reasoning (Self-Contra), where the model's reasoning contradicts its final answer, which is unacceptable in such a high-stakes domain. To address these challenges, we construct WeatherQA, a novel multimodal reasoning benchmark in meteorology. We also propose Logically Consistent Reinforcement Fine-Tuning (LoCo-RFT), which resolves Self-Contra by introducing a logical consistency reward. Furthermore, we introduce Weather-R1, the first reasoning VLM with logical faithfulness in meteorology, to the best of our knowledge. Experiments demonstrate that Weather-R1 improves performance on WeatherQA by 9.8 percentage points over the baseline, outperforming Supervised Fine-Tuning and RFT, and even surpassing the original Qwen2.5-VL-32B. These results highlight the effectiveness of our LoCo-RFT and the superiority of Weather-R1. Our benchmark and code are available at https://github.com/Marcowky/Weather-R1.