Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1. 1MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs2026
2. 2Assessing Modality Bias in Video Question Answering Benchmarks with Multimodal Large Language Models2024
3. 3BiasCause: Evaluate Socially Biased Causal Reasoning of Large Language Models2025
4. 4Beyond Spurious Signals: Debiasing Multimodal Large Language Models via Counterfactual Inference and Adaptive Expert Routing2025
5. 5Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models2025