# MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs

arXiv: https://arxiv.org/abs/2406.17126 · HTML: https://mlsanity.com/paper/2406.17126/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 63 of its 92 references that are in the map.
- First posted on arXiv 24 Jun 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 30 of 63)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)

## Built on by (most cited first, 30 of 33)

- [A Survey on Benchmarks of Multimodal Large Language Models](https://mlsanity.com/paper/2408.08632/) (2024)
- [MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs](https://mlsanity.com/paper/2411.15296/) (2024)
- [Visual Prompting in Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2409.15310/) (2024)
- [A Survey on Evaluation of Multimodal Large Language Models](https://mlsanity.com/paper/2408.15769/) (2024)
- [A Survey on Multimodal Benchmarks: In the Era of Large AI Models](https://mlsanity.com/paper/2409.18142/) (2024)
- [Unified Parameter-Efficient Unlearning for LLMs](https://mlsanity.com/paper/2412.00383/) (2024)
- [Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation](https://mlsanity.com/paper/2506.21876/) (2025)
- [HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation](https://mlsanity.com/paper/2505.11454/) (2025)
- [Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning](https://mlsanity.com/paper/2503.11832/) (2025)
- [Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations?](https://mlsanity.com/paper/2506.18322/) (2025)
- [Insect-Foundation: A Foundation Model and Large Multimodal Dataset for Vision-Language Insect Understanding](https://mlsanity.com/paper/2502.09906/) (2025)
- [SpurLens: Automatic Detection of Spurious Cues in Multimodal LLMs](https://mlsanity.com/paper/2503.08884/) (2025)
- [Structured Spectral Reasoning for Frequency-Adaptive Multimodal Recommendation](https://mlsanity.com/paper/2512.01372/) (2025)
- [Visual Instruction Bottleneck Tuning](https://mlsanity.com/paper/2505.13946/) (2025)
- [Directed-Tokens: A Robust Multi-Modality Alignment Approach to Large Language-Vision Models](https://mlsanity.com/paper/2508.14264/) (2025)
- [Beyond Spurious Signals: Debiasing Multimodal Large Language Models via Counterfactual Inference and Adaptive Expert Routing](https://mlsanity.com/paper/2509.15361/) (2025)
- [Measuring Agreeableness Bias in Multimodal Models](https://mlsanity.com/paper/2408.09111/) (2024)
- [GHOST: Hallucination-Inducing Image Generation for Multimodal LLMs](https://mlsanity.com/paper/2509.25178/) (2025)
- [SNS-Bench-VL: Benchmarking Multimodal Large Language Models in Social Networking Services](https://mlsanity.com/paper/2505.23065/) (2025)
- [Bias Beyond Demographics: Probing Decision Boundaries in Black-Box LVLMs via Counterfactual VQA](https://mlsanity.com/paper/2508.03079/) (2025)
- [Seeing Beyond the Scene: Analyzing and Mitigating Background Bias in Action Recognition](https://mlsanity.com/paper/2512.17953/) (2025)
- [Unbiased Visual Reasoning with Controlled Visual Inputs](https://mlsanity.com/paper/2512.22183/) (2025)
- [Prototypicality Bias Reveals Blindspots in Multimodal Evaluation Metrics](https://mlsanity.com/paper/2601.04946/) (2026)
- [The Role of Model Confidence on Bias Effects in Measured Uncertainties for Vision-Language Models](https://mlsanity.com/paper/2506.16724/) (2025)
- [SAGE: Spuriousness-Aware Guided Prompt Exploration for Mitigating Multimodal Bias](https://mlsanity.com/paper/2511.13005/) (2025)
- [FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance](https://mlsanity.com/paper/2602.02060/) (2026)
- [Verb Mirage: Unveiling and Assessing Verb Concept Hallucinations in Multimodal Large Language Models](https://mlsanity.com/paper/2412.04939/) (2024)
- [Evaluating Stochastic Collapse and Implicit Bias in Multimodal Large Language Models](https://mlsanity.com/paper/2606.05874/) (2026)
- [MotionHalluc: Diagnosing Kinematic Hallucinations in Fine-Grained Motion Reasoning](https://mlsanity.com/paper/2606.23061/) (2026)
- [MissingBench-Verified: Probing Vision-Language Models' Inability to Detect Missing Object Parts](https://mlsanity.com/paper/2607.18673/) (2026)

## Abstract (arXiv)

Spurious bias, a tendency to exploit spurious correlations between superficial input attributes and prediction targets, has revealed a severe robustness pitfall in classical machine learning problems. Multimodal Large Language Models (MLLMs), which leverage pretrained vision and language models, have recently demonstrated strong capability in joint vision-language understanding. However, both the presence and severity of spurious biases in MLLMs remain poorly understood. In this work, we address this gap by analyzing the spurious biases in the multimodal setting and uncovering the specific inference-time data patterns that can manifest this problem. To support this analysis, we introduce MM-SpuBench, a comprehensive, human-verified benchmark dataset consisting of image-class pairs annotated with core and spurious attributes, grounded in our taxonomy of nine distinct types of spurious correlations. The benchmark is constructed using human-interpretable attribute information to capture a wide range of spurious patterns reflective of real-world knowledge. Leveraging this benchmark, we conduct a comprehensive evaluation of the state-of-the-art open-source and proprietary MLLMs with both standard accuracy and the proposed Conditional Generation Likelihood Advantage (CGLA). Our findings highlight the persistence of reliance on spurious correlations and the difficulty of mitigation on our benchmark. We hope this work can inspire new technical strides to mitigate these biases. Our benchmark is publicly available at https://huggingface.co/datasets/mmbench/MM-SpuBench.