cs.AINov 19, 2026

When Safety Rationales Hallucinate: Diagnosing and Grounding Multimodal Safety Guards

Authors: Yingshuo Wang, Weixiang Zhao, Guancheng Li, Jiahe Guo, Yu Zhang, Yanyan Zhao

Organizations: Harbin Institute of Technology

Abstract

Multimodal safety guards increasingly generate rationales alongside safety predictions, yet whether these rationales are reliable remains largely unexplored. We systematically study rationale hallucination from two perspectives: visual rationale hallucination, where rationales contain unsupported visual facts, and safety attribution hallucination, where grounded content is assigned an incorrect safety interpretation. Across rationale-generation methods, multiple vision-language backbones, and safety datasets, we find that rationale hallucination is widespread and does not consistently diminish with higher classification accuracy or increased model scale. Further analysis of the Think-with-Image paradigm shows that hallucination is concentrated in fine-grained attributes and relations, while visual tools are often invoked infrequently or without sufficient spatial focus. Based on these findings, we propose Tool-Contrastive Grounding Reinforcement Learning (TCG-RL), which rewards tool use only when it improves rationale grounding over a tool-free reference. TCG-RL substantially reduces rationale hallucination while maintaining competitive safety prediction performance. By revealing the gap between prediction correctness and rationale reliability, our study motivates a shift in multimodal safety guarding from outcome-only evaluation toward safety decisions that are both accurate and verifiably grounded.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Feb 3, 2026

Seeing Through the Chain: Understanding and Mitigating Hallucinations in Multimodal Large Reasoning Models

While multimodal reasoning models (MLRMs) have exhibited impressive capabilities, they remain prone to hallucinations, and effective solutions are still underexplored. In this paper, we experimentally analyze the hallucination cause and propose C3PO, a training-based mitigation framework comprising Chain-of-Thought Compression and Contrastive Preference Optimization. Firstly, we identify that introducing reasoning mechanisms exacerbates models' reliance on language priors while overlooking visual inputs, which can produce CoTs with reduced visual cues but redundant text tokens. To this end, we propose to selectively filter redundant thinking tokens for a more compact and signal-efficient CoT representation that preserves task-relevant information while suppressing noise. In addition, we observe that the quality of the reasoning trace largely determines whether hallucination emerges in subsequent responses. To leverage this insight, we introduce a reasoning-enhanced preference tuning scheme that constructs training pairs using high-quality AI feedback. We further design a multimodal hallucination-inducing mechanism that elicits models' inherent hallucination patterns via carefully crafted inducers, yielding informative negative signals for contrastive correction. We provide theoretical justification for the effectiveness and demonstrate consistent hallucination reduction across diverse MLRMs and benchmarks.
Sep 29, 2026

ThinkingGuard: Decoding Implicit Hazards via Step-by-Step Risk Attribution in Multimodal Large Language Models

While Multimodal Large Language Models (MLLMs) are increasingly deployed in safety-critical domains, their reliability is threatened by multimodal implicit risks. Unlike explicit threats, these hazards emerge when individually benign text and neutral visual entities logically converge to induce unsafe outputs. Current detection methods fail to address this because they overlook the underlying risk activation mechanisms that govern cross-modal risk activation, leading to single-modality shortcut learning and hallucinated rationalizations. To bridge this gap, we first construct TriggerBench, the first dataset explicitly modeling risk compositionality (5,600 instances). By formally isolating Key Elements and Trigger Elements to build counterfactual contrastive pairs, TriggerBench eliminates risk residues and forces models to perform genuine logical deduction rather than superficial pattern matching, which provides a rigorous foundation for both large-scale training and fine-grained evaluation. Building on this, we propose a Step-Supervised Structured Reasoning training framework and employ it to train ThinkingGuard, a specialized guard model. Inspired by Situation Awareness theory, we decouple implicit risk identification into progressive cognitive stages, and utilize a step-reward Monte Carlo Tree Search algorithm to explore optimal reasoning trajectories, which are then distilled into the model through Dual-Constraint Preference Alignment. Extensive experiments across both standard and implicit safety benchmarks demonstrate that ThinkingGuard achieves strong performance. Project resources are available at https://github.com/FroggyChen/ThinkingGuard.
Sep 15, 2026

What Do Hallucinations Reveal About Multimodal Reasoning? Diagnosing Visual Grounding Failures via Contrastive Decoding Probes

When strong multimodal models are widely available, progress requires new scientific methodologies beyond benchmark scores---using models as instruments for understanding behavior. We address this by asking: can we use large vision-language models (LVLMs) as experimental instruments for studying their own failure dynamics? Focusing on visual hallucination, we introduce SAFE, a training-free decoding framework that contrasts visually-grounded and vision-ablated generation paths to produce a token-level contrastive grounding score that identifies when the model favors linguistic priors over visual evidence. This signal serves dual roles: as a practical proxy for detecting visually-ungrounded tokens, and as the basis for decoding-time penalties. Our analysis yields three empirical observations: visual dependency decays over generation, hallucinations co-occur in temporal clusters, and early intervention reduces clustering without substantially degrading fluency. On MMHalBench, SAFE substantially outperforms all compared baselines; results elsewhere are more mixed. We argue that designing contrastive probes exemplifies a broader mission: using models as instruments for scientific understanding. Code: https://github.com/zhaozhipeng1997/SAFE_public.