Awesome Papers for Understanding and Evaluating Modality Bias/Preference

Papers:

2025:

• Evaluating and Steering Modality Preferences in Multimodal Large Language Model
  • [2025.5] [evaluating] [steering] [model preference]
• WHY FOUNDATION MODELS STRUGGLE WITH CROSS-MODAL CONTEXT
  • [2025.3] [COLM2025] [evaluating] [multilingual] [model bias]
• MLLMs are Deeply Affected by Modality Bias
  • [2025.5] [evaluating] [model bias]
• How Do Vision-Language Models Process Conflicting Information Across Modalities?
  • [2025.6] [evaluating] [multimodal] [model bias]
• When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models
  • [2025.8] [evaluating] [modality bias] [video audio Graph Time-series]

2024:

• INSIGHT OVER SIGHT? EXPLORING THE VISIONKNOWLEDGE CONFLICTS IN MULTIMODAL LLMS
  • [2024.10] [ACL2025] [evaluating] [vision vs knowledge]
• DO VISION & LANGUAGE DECODERS USE IMAGES ANDTEXT EQUALLY? HOW SELF-CONSISTENT ARE THEIR EXPLANATIONS?
  • [2024.4] [ICLR2025] [evaluating] [model bias]
• MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs
  • [2024.6] [2024.10] [evaluating] [model bias]
• VLind-Bench: Measuring Language Priors in Large Vision-Language Models
  • [2024.6] [NAACL 2025 Findings] [evaluating] [language prior]
• Assessing Modality Bias in Video Question Answering Benchmarks with Multimodal Large Language Models
  • [2024.8] [AAAI2025] [evaluating] [model bias]
• IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations
  • [2024.8] [COLM2024] [evaluating]