Challenge: Existing evaluation methods to measure what language models learn from multimodal training are lacking.
Approach: They propose two evaluation tasks to measure commonsense knowledge in language models by using visual data to evaluate multimodal models and unimodal baselines.
Outcome: The proposed evaluation tasks show that training on a visual modality improves on the visual commonsense knowledge in language models.

Similar Papers

Visual Commonsense in Pretrained Unimodal and Multimodal Models (2022.naacl-main)

Copied to clipboard

Challenge: Fig. 1 shows how text-only and image-only models can capture commonsense visual attributes, but reporting bias affects their performance.
Approach: They use a Visual Commonsense Tests dataset to validate their findings . they find multimodal models better reconstruct attribute distributions, but are still subject to reporting bias .
Outcome: The proposed model improves on the unimodal and multimodal models, but is still subject to reporting bias.
Are Visual-Linguistic Models Commonsense Knowledge Bases? (2022.coling-1)

Copied to clipboard

Challenge: PTLMs are used to extract knowledge from text on demand.
Approach: They compare visual-linguistic and language-only visual-language models in a zero-shot commonsense question answering inference task.
Outcome: The proposed models are highly promising on certain types of commonsense knowledge associated with the visual world.
Understanding ME? Multimodal Evaluation for Fine-grained Visual Commonsense (2022.emnlp-main)

Copied to clipboard

Challenge: Existing models that understand image and text but also cross-reference in-between are lacking in evaluation data resources.
Approach: They propose a multimodal evaluation pipeline to automatically generate question-answer pairs to test models’ understanding of the visual scene, text, and related knowledge.
Outcome: The proposed model can answer the highly semantic VCR question correctly but fails to answer related visual question (Q2), textual question (q3), and background knowledge question ( Q4) as shallow mappings with language priors and unbalanced utilization of information between modalities.
Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models (2024.eacl-long)

Copied to clipboard

Challenge: Existing vision-and-language models perform better on multimodal tasks, but there is little understanding of how multimodal learning can help visual representations.
Approach: They conduct a probing analysis of visual representations in existing vision-and-language models and vision-only models by probing on a broad range of tasks.
Outcome: The proposed model improves vision-and-language models on label and attribute prediction tasks while vision-only models are stronger on dense prediction tasks.
Does Visual Grounding Enhance the Understanding of Embodied Knowledge in Large Language Models? (2025.findings-emnlp)

Copied to clipboard

Challenge: Despite significant progress in multimodal language models, it remains unclear whether visual grounding enhances their understanding of embodied knowledge compared to text-only models.
Approach: They propose to assess vision-language models’ perceptual abilities across different sensory modalities through vector comparison and question-answering tasks with over 1,700 questions.
Outcome: The proposed benchmark assesses the models’ perceptual abilities across different sensory modalities through vector comparison and question-answering tasks with over 1,700 questions.
How to Adapt Pre-trained Vision-and-Language Models to a Text-only Input? (2022.coling-1)

Copied to clipboard

Challenge: Current language models have been criticised for learning language from text alone without connection between words and their meaning.
Approach: They propose to train models on more sources than text to provide the lacking connection between words and their meanings.
Outcome: The proposed model adaptation methods perform differently for different models and unimodal model counterparts perform on par with the VL models regardless of adaptation.
A Systematic Investigation of Commonsense Knowledge in Large Language Models (2022.emnlp-main)

Copied to clipboard

Challenge: Recent large language models (LMs) have shown impressive performance on many NLP tasks under the zero-shot and few-shot setup.
Approach: They conduct a systematic and rigorous zero-shot and few-shot commonsense evaluation of large pre-trained language models to better understand their ability to capture commonsensical knowledge.
Outcome: The proposed model can exploit surface cues and annotation artefacts without task-specific supervision and is insufficient to achieve human-level commonsense performance.
Does Vision-and-Language Pretraining Improve Lexical Grounding? (2021.findings-emnlp)

Copied to clipboard

Challenge: Large pretrained language models (LMs) have been criticized for lack of grounding, i.e., connecting words to their meanings in the physical world.
Approach: They compare vision-and-language (VL) models trained jointly on text and image or video data to find out how they compare to text-only counterparts.
Outcome: The proposed model outperforms the text-only variants on a commonsense question answering task.
Visual Grounding Helps Learn Word Meanings in Low-Data Regimes (2024.naacl-long)

Copied to clipboard

Challenge: Modern neural language models (LMs) require distinctly un-human-like ways to achieve these results.
Approach: They train a diverse set of LM architectures with and without auxiliary visual supervision on datasets of varying scales.
Outcome: The proposed models exhibit better learning of syntactic categories, lexical relations, semantic features, word similarity and alignment with human neural representations.
Quantifying the Gaps Between Translation and Native Perception in Training for Multimodal, Multilingual Retrieval (2024.emnlp-main)

Copied to clipboard

Challenge: Existing models that account for perceptual differences in image captions are limited to use in English . culture-based tasks such as recognition, detection, and image retrieval are hindered by relying on English supervision.
Approach: They propose and evaluate caption augmentation strategies to address these gaps . they use captions from german perception and captions that have been machine-translated or human-transcribed from English into german .
Outcome: The proposed models achieve a mean recall improvement of +1.3, but still lack flexibility . cultural differences present in language with respect to object specificity and importance .

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