Paper
Physics-based phenomenological characterization of cross-modal bias in multimodal models
Authors
Hyeongmo Kim, Sohyun Kang, Yerin Choi, Seungyeon Ji, Junhyuk Woo, Hyunsuk Chung, Soyeon Caren Han, Kyungreem Han
Abstract
The term 'algorithmic fairness' is used to evaluate whether AI models operate fairly in both comparative (where fairness is understood as formal equality, such as "treat like cases as like") and non-comparative (where unfairness arises from the model's inaccuracy, arbitrariness, or inscrutability) contexts. Recent advances in multimodal large language models (MLLMs) are breaking new ground in multimodal understanding, reasoning, and generation; however, we argue that inconspicuous distortions arising from complex multimodal interaction dynamics can lead to systematic bias. The purpose of this position paper is twofold: first, it is intended to acquaint AI researchers with phenomenological explainable approaches that rely on the physical entities that the machine experiences during training/inference, as opposed to the traditional cognitivist symbolic account or metaphysical approaches; second, it is to state that this phenomenological doctrine will be practically useful for tackling algorithmic fairness issues in MLLMs. We develop a surrogate physics-based model that describes transformer dynamics (i.e., semantic network structure and self-/cross-attention) to analyze the dynamics of cross-modal bias in MLLM, which are not fully captured by conventional embedding- or representation-level analyses. We support this position through multi-input diagnostic experiments: 1) perturbation-based analyses of emotion classification using Qwen2.5-Omni and Gemma 3n, and 2) dynamical analysis of Lorenz chaotic time-series prediction through the physical surrogate. Across two architecturally distinct MLLMs, we show that multimodal inputs can reinforce modality dominance rather than mitigate it, as revealed by structured error-attractor patterns under systematic label perturbation, complemented by dynamical analysis.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2602.20624v1</id>\n <title>Physics-based phenomenological characterization of cross-modal bias in multimodal models</title>\n <updated>2026-02-24T07:21:08Z</updated>\n <link href='https://arxiv.org/abs/2602.20624v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2602.20624v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>The term 'algorithmic fairness' is used to evaluate whether AI models operate fairly in both comparative (where fairness is understood as formal equality, such as \"treat like cases as like\") and non-comparative (where unfairness arises from the model's inaccuracy, arbitrariness, or inscrutability) contexts. Recent advances in multimodal large language models (MLLMs) are breaking new ground in multimodal understanding, reasoning, and generation; however, we argue that inconspicuous distortions arising from complex multimodal interaction dynamics can lead to systematic bias. The purpose of this position paper is twofold: first, it is intended to acquaint AI researchers with phenomenological explainable approaches that rely on the physical entities that the machine experiences during training/inference, as opposed to the traditional cognitivist symbolic account or metaphysical approaches; second, it is to state that this phenomenological doctrine will be practically useful for tackling algorithmic fairness issues in MLLMs. We develop a surrogate physics-based model that describes transformer dynamics (i.e., semantic network structure and self-/cross-attention) to analyze the dynamics of cross-modal bias in MLLM, which are not fully captured by conventional embedding- or representation-level analyses. We support this position through multi-input diagnostic experiments: 1) perturbation-based analyses of emotion classification using Qwen2.5-Omni and Gemma 3n, and 2) dynamical analysis of Lorenz chaotic time-series prediction through the physical surrogate. Across two architecturally distinct MLLMs, we show that multimodal inputs can reinforce modality dominance rather than mitigate it, as revealed by structured error-attractor patterns under systematic label perturbation, complemented by dynamical analysis.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n <category scheme='http://arxiv.org/schemas/atom' term='cond-mat.stat-mech'/>\n <published>2026-02-24T07:21:08Z</published>\n <arxiv:comment>Best Paper Award at BiasinAI track in AAAI2026</arxiv:comment>\n <arxiv:primary_category term='cs.AI'/>\n <author>\n <name>Hyeongmo Kim</name>\n </author>\n <author>\n <name>Sohyun Kang</name>\n </author>\n <author>\n <name>Yerin Choi</name>\n </author>\n <author>\n <name>Seungyeon Ji</name>\n </author>\n <author>\n <name>Junhyuk Woo</name>\n </author>\n <author>\n <name>Hyunsuk Chung</name>\n </author>\n <author>\n <name>Soyeon Caren Han</name>\n </author>\n <author>\n <name>Kyungreem Han</name>\n </author>\n </entry>"
}