Metraipolis › archive › dc_c255d113aa17
Answer with Evidence: Consistency-Aware Grounded Visual Question Answering for Roadside Traffic Scenes — arXiv:2610.05274
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.05274
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:30:12.637Z
- SHA-256 of the archived text
57729a45e9b3a64df3a120e8cfa6f4ca6e1e5249e55dec393a4f72ca04ca65f1- Stable URL of this page
https://metraipolis.com/documento/dc_c255d113aa17
How to cite
Answer with Evidence: Consistency-Aware Grounded Visual Question Answering for Roadside Traffic Scenes — arXiv:2610.05274 — arXiv, https://arxiv.org/abs/2610.05274 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c255d113aa17 (Metraipolis archive dc_c255d113aa17, sha256 57729a45e9b3a64df3a120e8cfa6f4ca6e1e5249e55dec393a4f72ca04ca65f1)
BibTeX
@misc{dcc255d113aa17,
title = {Answer with Evidence: Consistency-Aware Grounded Visual Question Answering for Roadside Traffic Scenes — arXiv:2610.05274},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.05274},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c255d113aa17; sha256 57729a45e9b3a64df3a120e8cfa6f4ca6e1e5249e55dec393a4f72ca04ca65f1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05274. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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{ this https URL }.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.HC, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2610.05274 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T05:26:50.344Z dalla pagina https://arxiv.org/list/cs.HC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).