# MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?

arXiv: https://arxiv.org/abs/2406.17806 · HTML: https://mlsanity.com/paper/2406.17806/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 13 of its 34 references that are in the map.
- First posted on arXiv 22 Jun 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)

## Builds on (most cited first, 13 of 13)

- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models](https://mlsanity.com/paper/2311.17600/) (2023)
- [How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs](https://mlsanity.com/paper/2311.16101/) (2023)
- [A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation](https://mlsanity.com/paper/2305.11391/) (2023)
- [Identifying and Mitigating the Security Risks of Generative AI](https://mlsanity.com/paper/2308.14840/) (2023)
- [Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models](https://mlsanity.com/paper/2307.08487/) (2023)
- [LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?](https://mlsanity.com/paper/2307.10719/) (2023)
- [A Comprehensive Overview of Backdoor Attacks in Large Language Models within Communication Networks](https://mlsanity.com/paper/2308.14367/) (2023)
- [Detecting Harmful Content On Online Platforms: What Platforms Need Vs. Where Research Efforts Go](https://mlsanity.com/paper/2103.00153/) (2021)
- [How Far Are We from Intelligent Visual Deductive Reasoning?](https://mlsanity.com/paper/2403.04732/) (2024)

## Built on by (most cited first, 30 of 30)

- [MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs](https://mlsanity.com/paper/2411.15296/) (2024)
- [A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations](https://mlsanity.com/paper/2502.14881/) (2025)
- [VLSBench: Unveiling Visual Leakage in Multimodal Safety](https://mlsanity.com/paper/2411.19939/) (2024)
- [A Survey on Multimodal Benchmarks: In the Era of Large AI Models](https://mlsanity.com/paper/2409.18142/) (2024)
- [Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs](https://mlsanity.com/paper/2502.11184/) (2025)
- [Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models](https://mlsanity.com/paper/2501.18533/) (2025)
- [Aligning Multimodal LLM with Human Preference: A Survey](https://mlsanity.com/paper/2503.14504/) (2025)
- [SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization](https://mlsanity.com/paper/2511.12982/) (2025)
- [USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2505.23793/) (2025)
- [Beyond Surface-Level Patterns: An Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs](https://mlsanity.com/paper/2502.19041/) (2025)
- [VLSU: Mapping the Limits of Joint Multimodal Understanding for AI Safety](https://mlsanity.com/paper/2510.18214/) (2025)
- [Steering Multimodal Large Language Models Decoding for Context-Aware Safety](https://mlsanity.com/paper/2509.19212/) (2025)
- [ORFuzz: Fuzzing the "Other Side" of LLM Safety -- Testing Over-Refusal](https://mlsanity.com/paper/2508.11222/) (2025)
- [DUAL-Bench: Measuring Over-Refusal and Robustness in Vision-Language Models](https://mlsanity.com/paper/2510.10846/) (2025)
- [VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration](https://mlsanity.com/paper/2505.20362/) (2025)
- [Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective Memory](https://mlsanity.com/paper/2603.15800/) (2026)
- [When Safe Unimodal Inputs Collide: Optimizing Reasoning Chains for Cross-Modal Safety in Multimodal Large Language Models](https://mlsanity.com/paper/2509.12060/) (2025)
- [MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues](https://mlsanity.com/paper/2601.06757/) (2026)
- [When Helpers Become Hazards: A Benchmark for Analyzing Multimodal LLM-Powered Safety in Daily Life](https://mlsanity.com/paper/2601.04043/) (2026)
- [Auditing Multimodal LLM Raters: Central Tendency Bias in Clinical Ordinal Scoring](https://mlsanity.com/paper/2605.16386/) (2026)
- [How Jailbreak Defenses Work and Ensemble? A Mechanistic Investigation](https://mlsanity.com/paper/2502.14486/) (2025)
- [CSR-Bench: A Benchmark for Evaluating the Cross-modal Safety and Reliability of MLLMs](https://mlsanity.com/paper/2602.03263/) (2026)
- [Reimagining Safety Alignment with An Image](https://mlsanity.com/paper/2511.00509/) (2025)
- [Does Unification Come at a Cost? Uni-SafeBench: A Safety Benchmark for Unified Multimodal Large Models](https://mlsanity.com/paper/2604.00547/) (2026)
- [Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs](https://mlsanity.com/paper/2604.08846/) (2026)
- [AOR-Bench: Do Large Audio Language Models Over-Refuse Pseudo-Harmful Queries?](https://mlsanity.com/paper/2606.21147/) (2026)
- [A2Safe: Counterfactual Evidence-Aligned Adaptive Agent Collaboration for Safe and Effective Visual Question Answering](https://mlsanity.com/paper/2609.24098/) (2026)
- [Can Vision-Language Models Stay Helpful When Facing Implicit Risks? Intent-Privilege OPSD for Efficient Safety-Helpfulness Alignment](https://mlsanity.com/paper/2609.37837/) (2026)
- [False Floors: LLM Safety Routing Evaluations Break Under Distribution Shift](https://mlsanity.com/paper/2610.01535/) (2026)
- [Visual Grounding Safety in Vision-Language Models](https://mlsanity.com/paper/2610.05637/) (2026)

## Abstract (arXiv)

Humans are prone to cognitive distortions -- biased thinking patterns that lead to exaggerated responses to specific stimuli, albeit in very different contexts. This paper demonstrates that advanced Multimodal Large Language Models (MLLMs) exhibit similar tendencies. While these models are designed to respond queries under safety mechanism, they sometimes reject harmless queries in the presence of certain visual stimuli, disregarding the benign nature of their contexts. As the initial step in investigating this behavior, we identify three types of stimuli that trigger the oversensitivity of existing MLLMs: Exaggerated Risk, Negated Harm, and Counterintuitive Interpretation. To systematically evaluate MLLMs' oversensitivity to these stimuli, we propose the Multimodal OverSenSitivity Benchmark (MOSSBench). This toolkit consists of 300 manually collected benign multimodal queries, cross-verified by third-party reviewers (AMT). Empirical studies using MOSSBench on 20 MLLMs reveal several insights: (1). Oversensitivity is prevalent among SOTA MLLMs, with refusal rates reaching up to 76% for harmless queries. (2). Safer models are more oversensitive: increasing safety may inadvertently raise caution and conservatism in the model's responses. (3). Different types of stimuli tend to cause errors at specific stages -- perception, intent reasoning, and safety judgement -- in the response process of MLLMs. These findings highlight the need for refined safety mechanisms that balance caution with contextually appropriate responses, improving the reliability of MLLMs in real-world applications. We make our project available at https://turningpoint-ai.github.io/MOSSBench/.