@inproceedings{dong-etal-2026-mitigating,
    title = "Mitigating Safety Context Amnesia in Multimodal Reasoning Models via Intent-Guided Safety Reasoning",
    author = "Dong, Xiyao  and
      Cheng, Guangsheng  and
      Chen, YiLong  and
      Zhang, Xiaojin  and
      He, Kun",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1821/",
    pages = "39249--39276",
    ISBN = "979-8-89176-390-6",
    abstract = "Recent advances in Multimodal Large Reasoning Models (MLRMs) have enabled explicit chain-of-thought inference across vision and language, substantially improving performance on complex reasoning tasks. Despite these gains, the reasoning process introduces a subtle yet critical vulnerability. We identify an underexplored multimodal safety failure mode in which harmful objectives are embedded within ostensibly benign contexts, leading models to over-prioritize narrative coherence during reasoning. We term this phenomenon Safety Context Amnesia (SCA), wherein models correctly perceive risk-relevant visual cues but fail to enforce safety constraints as the reasoning process becomes dominated by contextual alignment. To mitigate SCA, we propose Intent-Guided Safety Reasoning (IGSR), an inference-time defense that operates without modifying target model parameters. IGSR employs a Perception Decoupler to extract objective visual evidence into a structured intent output, followed by a Cognitive Arbiter that enforces explicit safety constraints prior to generation. Extensive experiments across multiple multimodal safety benchmarks demonstrate that IGSR improves defense success rates by over 62{\%} compared to baselines, while largely preserving task utility. These results highlight the critical role of structured, intent-aware reasoning in achieving robust safety reasoning for multimodal reasoning models."
}