paper-with-me

Papers

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

2026-09-04 · Davide Testa, Hugh Mee Wong, Alessandro Lenci, Bernardo Magnini, Albert Gatt 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.

📄 PDF Abstract BibTeX arXiv:2609.05149

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Reasoning

Similar Papers 제목 키워드 기반

Investigating Gender Bias in Language Models Using Causal Mediation Analysis

2020-12-01 · NeurIPS 2020 12 · Jesse Vig, Sebastian Gehrmann, Yonatan Belinkov, Sharon Qian 외

Many interpretation methods for neural models in natural language processing investigate how information is encoded inside hidden representations. However, these methods can only measure whether the information exists, n…

InfoFlowNet: A Multi-head Attention-based Self-supervised Learning Model with Surrogate Approach for Uncovering Brain Effective Connectivity

2023-11-30 · Chun-Hsiang Chuang, Shao-Xun Fang, Chih-Sheng Huang, Weiping Ding

Deciphering brain network topology can enhance the depth of neuroscientific knowledge and facilitate the development of neural engineering methods. Effective connectivity, a measure of brain network dynamics, is particul…

Causal DiscoveryCausal InferenceEEGElectroencephalogram (EEG)+2

TranCIT: Transient Causal Interaction Toolbox

2025-08-30 · Salar Nouri, Kaidi Shao, Shervin Safavi arxiv

Quantifying transient causal interactions from non-stationary neural signals is a fundamental challenge in neuroscience. Traditional methods are often inadequate for brief neural events, and advanced, event-specific tech…

Investigating Relational Reasoning in VLMs

2026-08-24 · Adhithya Laxman Ravi Shankar Geetha, Aulia Kharis Rakhmasari, Haleema Ramzan, Xander Yap arxiv

Vision-Language Models (VLMs) achieve strong performance in visual reasoning tasks, but it remains unclear whether they understand visual relations, or simply employ shortcuts such as language cues or priors. To investig…

Relational ReasoningVisual Reasoning

Marginal Causal Flows for Validation and Inference

2024-11-02 · Daniel de Vassimon Manela, Laura Battaglia, Robin J. Evans

Investigating the marginal causal effect of an intervention on an outcome from complex data remains challenging due to the inflexibility of employed models and the lack of complexity in causal benchmark datasets, which o…

Normalising Flows