# From Vision to Language: Investigating Causal Information Flow in Multimodal Decision-Making

arXiv: https://arxiv.org/abs/2609.05149 · HTML: https://mlsanity.com/paper/2609.05149/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 4 Sep 2026.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 27 of 27)

- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [TempCompass: Do Video LLMs Really Understand Videos?](https://mlsanity.com/paper/2403.00476/) (2024)
- [VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena](https://mlsanity.com/paper/2112.07566/) (2021)
- [FOIL it! Find One mismatch between Image and Language caption](https://mlsanity.com/paper/1705.01359/) (2017)
- [Language Model Behavior: A Comprehensive Survey](https://mlsanity.com/paper/2303.11504/) (2023)
- [Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding](https://mlsanity.com/paper/2503.06287/) (2025)
- [Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries](https://mlsanity.com/paper/2406.12775/) (2024)
- [MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks](https://mlsanity.com/paper/2212.08158/) (2022)
- [Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals](https://mlsanity.com/paper/2402.11655/) (2024)
- [Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective](https://mlsanity.com/paper/2403.18346/) (2024)
- [From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks](https://mlsanity.com/paper/2406.06579/) (2024)
- [Seeing past words: Testing the cross-modal capabilities of pretrained V&L models on counting tasks](https://mlsanity.com/paper/2012.12352/) (2020)
- [ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models](https://mlsanity.com/paper/2311.07022/) (2023)
- [VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors](https://mlsanity.com/paper/2604.02486/) (2026)
- [A Study into Investigating Temporal Robustness of LLMs](https://mlsanity.com/paper/2503.17073/) (2025)
- [Defoiling Foiled Image Captions](https://mlsanity.com/paper/1805.06549/) (2018)
- [How Vision Becomes Language: A Layer-wise Information-Theoretic Analysis of Multimodal Reasoning](https://mlsanity.com/paper/2602.15580/) (2026)
- [Burn After Reading: Do Multimodal Large Language Models Truly Capture Order of Events in Image Sequences?](https://mlsanity.com/paper/2506.10415/) (2025)
- [Deep Temporal Reasoning in Video Language Models: A Cross-Linguistic Evaluation of Action Duration and Completion through Perfect Times](https://mlsanity.com/paper/2506.00928/) (2025)
- [All-in-one: Understanding and Generation in Multimodal Reasoning with the MAIA Benchmark](https://mlsanity.com/paper/2502.16989/) (2025)

## Abstract (arXiv)

Vision-Language Models are commonly evaluated through their final predictions, but understanding whether these decisions are grounded in visual evidence requires tracing how visual information contributes to language-based decisions. With this purpose in mind, we investigate cross-modal information flow in a video-based generative multiple-choice-like setting by applying a layer-wise causal intervention on video-text attention pathways. We target spatial, causal, and temporal visual reasoning. Our results show that visual information is mainly integrated while the model processes the candidate answer options, which serve as the primary textual grounding sites for the final decision. We further show that nouns play an important role as semantic anchors during multimodal enrichment, while verbs are more relevant when temporal relations are processed. Finally, we identify a distinct pattern in temporal reasoning, suggesting that VLMs struggle to reconstruct sequential information across video frames, but we remark that such fragility may also reflect linguistic biases associated with specific temporal expressions used for defining the relation between events within a scene.