# Self-Captioning Multimodal Interaction Tuning: Amplifying Exploitable Redundancies for Robust Vision Language Models

arXiv: https://arxiv.org/abs/2605.08145 · HTML: https://mlsanity.com/paper/2605.08145/

## Key facts

- No citing papers in the map yet (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 36 of its 45 references that are in the map.
- First posted on arXiv 3 May 2026.

## 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 36)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Are We on the Right Way for Evaluating Large Vision-Language Models?](https://mlsanity.com/paper/2403.20330/) (2024)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models](https://mlsanity.com/paper/2310.14566/) (2023)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [What matters when building vision-language models?](https://mlsanity.com/paper/2405.02246/) (2024)
- [SmolVLM: Redefining small and efficient multimodal models](https://mlsanity.com/paper/2504.05299/) (2025)
- [Multi-Modal Hallucination Control by Visual Information Grounding](https://mlsanity.com/paper/2403.14003/) (2024)
- [Building and better understanding vision-language models: insights and future directions](https://mlsanity.com/paper/2408.12637/) (2024)
- [UR-FUNNY: A Multimodal Language Dataset for Understanding Humor](https://mlsanity.com/paper/1904.06618/) (2019)
- [Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework](https://mlsanity.com/paper/2302.12247/) (2023)
- [Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models](https://mlsanity.com/paper/2410.03577/) (2024)
- [Enhancing Large Vision Language Models with Self-Training on Image Comprehension](https://mlsanity.com/paper/2405.19716/) (2024)
- [The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering](https://mlsanity.com/paper/2502.03628/) (2025)
- [Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance](https://mlsanity.com/paper/2402.08680/) (2024)
- [Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models](https://mlsanity.com/paper/2306.02080/) (2023)
- [I2MoE: Interpretable Multimodal Interaction-aware Mixture-of-Experts](https://mlsanity.com/paper/2505.19190/) (2025)
- [A Rigorous Information-Theoretic Definition of Redundancy and Relevancy in Feature Selection Based on (Partial) Information Decomposition](https://mlsanity.com/paper/2105.04187/) (2021)
- [Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications](https://mlsanity.com/paper/2306.04539/) (2023)
- [A Differential Entropy Estimator for Training Neural Networks](https://mlsanity.com/paper/2202.06618/) (2022)
- [DiffusionPID: Interpreting Diffusion via Partial Information Decomposition](https://mlsanity.com/paper/2406.05191/) (2024)
- [Measuring Cross-Modal Interactions in Multimodal Models](https://mlsanity.com/paper/2412.15828/) (2024)
- [Measuring multivariate redundant information with pointwise common change in surprisal](https://mlsanity.com/paper/1602.05063/) (2016)

## Abstract (arXiv)

Current vision language models face hallucination and robustness issues against ambiguous or corrupted modalities. We hypothesize that these issues can be addressed by exploiting the shared information between modalities to compensate for the impaired one. To this end, we analyze multimodal interactions -- redundant (shared), unique (exclusive), and synergistic (emergent) task-relevant information provided by the modalities -- to determine their impacts on model reliability. Specifically, amplifying redundant interactions would increase this exploitable shared information to resolve these issues; yet, modern instruction datasets often eliminate redundancies to prioritize visual grounding. We bridge this gap through a self-captioning workflow featuring a textscMultimodal Interaction Gate: a mechanism to convert unique interactions into redundant interactions. Our findings suggest that increasing redundancy can reduce visual induced errors by 38.3% and improve consistency by 16.8%.