Challenge: Lack of visual grounding (VG) in VQA systems can manifest in over-reliance on irrelevant image parts or a disregard for the visual modality entirely.
Approach: They propose a new metric that measures if a model identifies question-relevant objects in the scene and relies on the information contained in the relevant objects when producing its answer.
Outcome: The proposed metric measures if a model identifies question-relevant objects in the scene and relies on the information contained in the relevant objects when producing its answer.

Similar Papers

Uncovering the Full Potential of Visual Grounding Methods in VQA (2024.acl-long)

Copied to clipboard

Challenge: Visual Grounding (VG) methods in VQA aim to strengthen a model's reliance on question-relevant visual information.
Approach: They propose to strengthen a model's reliance on question-relevant visual information by using a visual grounding method that is based on a question-related visual input.
Outcome: The proposed methods can be much more effective when evaluation conditions are corrected.
A negative case analysis of visual grounding methods for VQA (2020.acl-main)

Copied to clipboard

Challenge: Existing Visual Question Answering (VQA) methods exploit dataset biases and spurious statistical correlations instead of producing correct answers for the right reasons.
Approach: They propose to incorporate visual cues to better ground VQA models . they also propose a regularization effect which prevents over-fitting to linguistic priors .
Outcome: The proposed method outperforms existing methods on the Visual Question Answering (VQA) dataset.
CommVQA: Situating Visual Question Answering in Communicative Contexts (2024.emnlp-main)

Copied to clipboard

Challenge: Current visual question answering models are trained on image-question pairs in isolation, but the questions people ask are dependent on their informational needs and prior knowledge about the image content.
Approach: They propose a visual question-answer-as-question dataset that contains 1000 images and 8,949 question-announcer pairs to evaluate how situating images within naturalistic contexts shapes visual questions.
Outcome: The proposed dataset contains 1000 images and 8,949 question-answer pairs.
Where is this coming from? Making groundedness count in the evaluation of Document VQA models (2025.findings-naacl)

Copied to clipboard

Challenge: Document Visual Question Answering (VQA) models have come close to or matching human performance on some benchmarks.
Approach: They propose a method that accounts for the semantic and multimodal groundedness of a model’s outputs and can be parameterized so that users can configure the score according to their preferences.
Outcome: The proposed method produces scores that are a better indicator of a model’s robustness and tends to give higher rewards to better-calibrated answers.
‘Just because you are right, doesn’t mean I am wrong’: Overcoming a bottleneck in development and evaluation of Open-Ended VQA tasks (2021.eacl-main)

Copied to clipboard

Challenge: Existing visual question answering datasets assume only one ground truth answer for each question.
Approach: They propose alternative answer sets (AAS) of ground-truth answers to address this limitation . they modify top VQA solvers to support multiple plausible answers for a question .
Outcome: The proposed approach improves on the GQA dataset and shows that it is more efficient than previous approaches.
ProtoVQA: An Adaptable Prototypical Framework for Explainable Fine-Grained Visual Question Answering (2025.emnlp-main)

Copied to clipboard

Challenge: Visual Question Answering (VQA) is increasingly used in diverse applications where models must provide accurate answers and explanations that humans can easily understand and verify.
Approach: They propose a unified prototypical framework that learns question-aware prototypes that serve as reasoning anchors and applies spatially constrained matching to ensure that the selected evidence is coherent and semantically relevant.
Outcome: The proposed framework yields faithful, fine-grained explanations while maintaining competitive accuracy.
Sunny and Dark Outside?! Improving Answer Consistency in VQA through Entailed Question Generation (D19-1)

Copied to clipboard

Challenge: interacting with a model for Visual Question Answering (VQA) quickly reveals that these models lack consistency.
Approach: They propose a dataset, ConVQA, and metrics that enable quantitative evaluation of consistency in VQA.
Outcome: The proposed data augmentation module improves the consistency of VQA models on the Con-VQA dataset and is a strong baseline for future research.
MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering (2025.findings-acl)

Copied to clipboard

Challenge: Existing Large Vision-Language Models (LVLMs) lack integrated commonsense knowledge . lack of integrated common knowledge limits their robustness and accuracy in VQA .
Approach: They propose a framework to enhance multimodal inference by integrating commonsense reasoning.
Outcome: MAGIC-VQA improves comprehensive benchmark datasets, surpassing existing models in tasks requiring advanced commonsense reasoning.
Selectively Answering Visual Questions (2024.findings-acl)

Copied to clipboard

Challenge: Large multi-modal models (LMMs) are capable of visual question answering (VQA) with unprecedented accuracy.
Approach: They propose a calibration score that can be used to quantify uncertainty in visual question answering models.
Outcome: The proposed calibration score is better calibrated than in text-only models for in-context learning.
Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions (2021.acl-short)

Copied to clipboard

Challenge: Existing systems for visual question answering are overfitted to training data and are sensitive to small perturbations.
Approach: They propose a robustness measure to augment visual question answering datasets to measure generalization capabilities.
Outcome: The proposed model can quantify failure cases which reveal that current systems are still brittle.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations