# Assessing Modality Bias in Video Question Answering Benchmarks with Multimodal Large Language Models

arXiv: https://arxiv.org/abs/2408.12763 · HTML: https://mlsanity.com/paper/2408.12763/

## Key facts

- Cited by 23 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 17 of its 24 references that are in the map.
- First posted on arXiv 22 Aug 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, 17 of 17)

- [NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions](https://mlsanity.com/paper/2105.08276/) (2021)
- [VGGSound: A Large-scale Audio-Visual Dataset](https://mlsanity.com/paper/2004.14368/) (2020)
- [ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering](https://mlsanity.com/paper/1906.02467/) (2019)
- [TVQA: Localized, Compositional Video Question Answering](https://mlsanity.com/paper/1809.01696/) (2018)
- [Zero-Shot Video Question Answering via Frozen Bidirectional Language Models](https://mlsanity.com/paper/2206.08155/) (2022)
- [VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling](https://mlsanity.com/paper/2111.12681/) (2021)
- [MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound](https://mlsanity.com/paper/2201.02639/) (2022)
- [All in One: Exploring Unified Video-Language Pre-training](https://mlsanity.com/paper/2203.07303/) (2022)
- [TVQA+: Spatio-Temporal Grounding for Video Question Answering](https://mlsanity.com/paper/1904.11574/) (2019)
- [VindLU: A Recipe for Effective Video-and-Language Pretraining](https://mlsanity.com/paper/2212.05051/) (2022)
- [Video Question Answering: Datasets, Algorithms and Challenges](https://mlsanity.com/paper/2203.01225/) (2022)
- [An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling](https://mlsanity.com/paper/2209.01540/) (2022)
- [Modality Shifting Attention Network for Multi-modal Video Question Answering](https://mlsanity.com/paper/2007.02036/) (2020)
- [Perceptual Score: What Data Modalities Does Your Model Perceive?](https://mlsanity.com/paper/2110.14375/) (2021)
- [MMFT-BERT: Multimodal Fusion Transformer with BERT Encodings for Visual Question Answering](https://mlsanity.com/paper/2010.14095/) (2020)
- [Self-supervised pre-training and contrastive representation learning for multiple-choice video QA](https://mlsanity.com/paper/2009.08043/) (2020)
- [Quantifying and Enhancing Multi-modal Robustness with Modality Preference](https://mlsanity.com/paper/2402.06244/) (2024)

## Built on by (most cited first, 23 of 23)

- [MLLMs are Deeply Affected by Modality Bias](https://mlsanity.com/paper/2505.18657/) (2025)
- [Evaluating and Steering Modality Preferences in Multimodal Large Language Model](https://mlsanity.com/paper/2505.20977/) (2025)
- [Benchmark Designers Should "Train on the Test Set" to Expose Exploitable Non-Visual Shortcuts](https://mlsanity.com/paper/2511.04655/) (2025)
- [Securing Large Language Models: Addressing Bias, Misinformation, and Prompt Attacks](https://mlsanity.com/paper/2409.08087/) (2024)
- [Enhanced Multimodal RAG-LLM for Accurate Visual Question Answering](https://mlsanity.com/paper/2412.20927/) (2024)
- [Multi-speaker Attention Alignment for Multimodal Social Interaction](https://mlsanity.com/paper/2511.17952/) (2025)
- [XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models](https://mlsanity.com/paper/2510.15148/) (2025)
- [Watch Before You Answer: Learning from Visually Grounded Post-Training](https://mlsanity.com/paper/2604.05117/) (2026)
- [To Judge or not to Judge: Using LLM Judgements for Advertiser Keyphrase Relevance at eBay](https://mlsanity.com/paper/2505.04209/) (2025)
- [AMPS: Adaptive Modality Preference Steering via Functional Entropy](https://mlsanity.com/paper/2602.12533/) (2026)
- [Unleashing the Intrinsic Visual Representation Capability of Multimodal Large Language Models](https://mlsanity.com/paper/2512.06281/) (2025)
- [Beyond Perceptual Shortcuts: Causal-Inspired Debiasing Optimization for Generalizable Video Reasoning in Lightweight MLLMs](https://mlsanity.com/paper/2605.01324/) (2026)
- [Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs](https://mlsanity.com/paper/2605.13737/) (2026)
- [Uncertainty-Weighted Fusion of Image and Synthetic Event for Video Anomaly Detection](https://mlsanity.com/paper/2505.02393/) (2025)
- [Benchmarking the Trustworthiness in Multimodal LLMs for Video Understanding](https://mlsanity.com/paper/2506.12336/) (2025)
- [Stress Tests REVEAL Fragile Temporal and Visual Grounding in Video-Language Models](https://mlsanity.com/paper/2602.11244/) (2026)
- [Information Router for Mitigating Modality Dominance in Vision-Language Models](https://mlsanity.com/paper/2604.16264/) (2026)
- [Overview of the NLPCC 2026 Shared Task 1: Difficulty-Aware Multilingual and Multimodal Medical Instructional Video Understanding Evaluation](https://mlsanity.com/paper/2607.06618/) (2026)
- [A Video Is Not Worth a Thousand Words](https://mlsanity.com/paper/2510.23253/) (2025)
- [HLTCOE Evaluation Team at TREC 2025: VQA Track](https://mlsanity.com/paper/2512.07738/) (2025)
- [Characterizing the Predictive Impact of Modalities with Supervised Latent-Variable Modeling](https://mlsanity.com/paper/2602.16979/) (2026)
- [CogniRoute: Learning to Route Social Evidence in Omni-Modal Models](https://mlsanity.com/paper/2606.20970/) (2026)
- [Mitigating Cross-Modal Hallucinations by Correcting Modality Misrouting in Omnimodal LLMs](https://mlsanity.com/paper/2610.18141/) (2026)

## Abstract (arXiv)

Multimodal large language models (MLLMs) can simultaneously process visual, textual, and auditory data, capturing insights that complement human analysis. However, existing video question-answering (VidQA) benchmarks and datasets often exhibit a bias toward a single modality, despite the goal of requiring advanced reasoning skills that integrate diverse modalities to answer the queries. In this work, we introduce the modality importance score (MIS) to identify such bias. It is designed to assess which modality embeds the necessary information to answer the question. Additionally, we propose an innovative method using state-of-the-art MLLMs to estimate the modality importance, which can serve as a proxy for human judgments of modality perception. With this MIS, we demonstrate the presence of unimodal bias and the scarcity of genuinely multimodal questions in existing datasets. We further validate the modality importance score with multiple ablation studies to evaluate the performance of MLLMs on permuted feature sets. Our results indicate that current models do not effectively integrate information due to modality imbalance in existing datasets. Our proposed MLLM-derived MIS can guide the curation of modality-balanced datasets that advance multimodal learning and enhance MLLMs' capabilities to understand and utilize synergistic relations across modalities.