Metraipolis › archive › dc_303c491ac4cf
From Sports to Safety: Benchmarking Proactive Risk Inference in MLLMs — arXiv:2608.05560
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.05560
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-25T21:31:01.383Z
- SHA-256 of the archived text
7f3576638d3577592147f113fb457958a7cde4751de6420e062927ffdc300354- Stable URL of this page
https://metraipolis.com/documento/dc_303c491ac4cf
How to cite
From Sports to Safety: Benchmarking Proactive Risk Inference in MLLMs — arXiv:2608.05560 — arXiv (en), https://arxiv.org/abs/2608.05560 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_303c491ac4cf (Metraipolis archive dc_303c491ac4cf, sha256 7f3576638d3577592147f113fb457958a7cde4751de6420e062927ffdc300354)
BibTeX
@misc{dc303c491ac4cf,
title = {From Sports to Safety: Benchmarking Proactive Risk Inference in MLLMs — arXiv:2608.05560},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.05560},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_303c491ac4cf; sha256 7f3576638d3577592147f113fb457958a7cde4751de6420e062927ffdc300354},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05560. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Timely anticipation of physical hazards is essential for real-world safety, yet existing MLLM evaluations focus on harmful content or general risks, leaving proactive physical hazard prediction underexplored. Sports provide a well-suited testbed: accident causes span diverse injury dimensions and pre-accident spatiotemporal cues draw on reasoning capabilities shared with broader safety domains such as autonomous driving and fall detection. We introduce SPRINT (Sports Proactive Risk INference Testbed), a benchmark of 2,888 real-world sports videos (2,440 accident, 448 safe controls) spanning 14 sports and 3 environmental settings. Accident videos feature fine-grained annotations of early hazard cues, accident timing, and hierarchical causes; safe videos are manually verified as accident-free and serve to diagnose prompt-induced false alarms. Evaluating state-of-the-art MLLMs under diverse prompts and temporal windows reveals a sharp gap between hazard sensitivity and understanding: the best model exceeds 95% in signaling hazards yet falls below 50% in identifying their causes. Diagnostic experiments further show that explicit danger queries trigger severe false alarms even on hazard-free videos. These findings indicate that current MLLMs exhibit only superficial proactive safety, lacking stable, cause-grounded early warning, and underscore the need for reliable proactive safety in dynamic physical environments. Data and code will be open-sourced upon acceptance. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CL). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.05560 — 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 2026-10-25T21:24:38.253Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).