Abstract
Roadside traffic reasoning requires every free-form textual claim to be backed by visual evidence. Existing grounded multimodal large language models (MLLMs) frequently exhibit say-point mismatch, in which the textual answer contradicts the bounding boxes the model localizes. Evaluation metrics that score answers and boxes separately leave this failure unpenalized. We trace the mismatch to the conventional answer-then-ground factorization, which commits to a numerical claim before any object is enumerated. To measure it, we build RoadSceneVQA-G, a benchmark of 34.7K question-answer pairs in which every free-form answer is linked to the set of boxes that witnesses it, and we propose the Answer-Grounding Consistency (AGC) evaluation suite. To address it, we introduce Enumerate-then-Answer (EtA), which reverses the generation order so that answer-evidence agreement becomes a property of the output structure, and Enumeration-Consistent Policy Optimization (ECPO), a reinforcement learning stage that uses the union of multiple rollouts as a recall teacher without ground-truth boxes. EtA raises say-point consistency from 26.6\% to 93.7\% and grounding F1 from 52.2\% to 73.0\%, and ECPO further increases F1 to 75.6\% without per-box supervision. On gRefCOCO, the same framework outperforms the strongest compared method, indicating that it transfers beyond traffic scenes. The project is available at \url{https://github.com/GuanRunwei/RoadSceneVQA-G}.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Guan, R., Hu, R., Chen, S., Ouyang, N., Liang, S., Lin, H., Zhu, J., Shi, Y., Wu, D., Liu, D., Ding, H., & Xiong, H. (2026). Answer with Evidence: Consistency-Aware Grounded Visual Question Answering for Roadside Traffic Scenes. https://omanscience.com/en/articles/answer-with-evidence-consistency-aware-grounded-visual-question-answering-for-roadside-traffic-scenes
MLA 9
Guan, Runwei, et al. "Answer with Evidence: Consistency-Aware Grounded Visual Question Answering for Roadside Traffic Scenes." https://omanscience.com/en/articles/answer-with-evidence-consistency-aware-grounded-visual-question-answering-for-roadside-traffic-scenes.
Chicago (author–date)
Guan, Runwei, Rongsheng Hu, Shangshu Chen, Ningwei Ouyang, Shaofeng Liang, Heyi Lin, Jinjing Zhu, Yang Shi, Dongming Wu, Daizong Liu, Henghui Ding, and Hui Xiong. 2026. "Answer with Evidence: Consistency-Aware Grounded Visual Question Answering for Roadside Traffic Scenes." https://omanscience.com/en/articles/answer-with-evidence-consistency-aware-grounded-visual-question-answering-for-roadside-traffic-scenes.
Harvard
Guan, R., Hu, R., Chen, S., Ouyang, N., Liang, S., Lin, H., Zhu, J., Shi, Y., Wu, D., Liu, D., Ding, H. and Xiong, H. (2026) 'Answer with Evidence: Consistency-Aware Grounded Visual Question Answering for Roadside Traffic Scenes', Available at: https://omanscience.com/en/articles/answer-with-evidence-consistency-aware-grounded-visual-question-answering-for-roadside-traffic-scenes.
Vancouver
Guan R, Hu R, Chen S, Ouyang N, Liang S, Lin H, et al. Answer with Evidence: Consistency-Aware Grounded Visual Question Answering for Roadside Traffic Scenes. https://omanscience.com/en/articles/answer-with-evidence-consistency-aware-grounded-visual-question-answering-for-roadside-traffic-scenes
IEEE
R. Guan, R. Hu, S. Chen, N. Ouyang, S. Liang, H. Lin, J. Zhu, Y. Shi, D. Wu, D. Liu, H. Ding, and H. Xiong, "Answer with Evidence: Consistency-Aware Grounded Visual Question Answering for Roadside Traffic Scenes," https://omanscience.com/en/articles/answer-with-evidence-consistency-aware-grounded-visual-question-answering-for-roadside-traffic-scenes.