Challenge: Existing vision-language models overemphasize linguistic priors, leading to modality bias.
Approach: They propose a vision-language aggregation framework that mitigates modality bias in TAL by preserving vision as the dominant signal while adaptively exploiting language only when beneficial.
Outcome: Experiments on THUMOS14 show that the proposed model outperforms state-of-the-art models by up to 3.2% mAP.

Similar Papers

Stable Language Guidance for Vision–Language–Action Models (2026.acl-long)

Copied to clipboard

Challenge: Existing vision-Language-Action models are notoriously brittle to linguistic perturbations.
Approach: They propose a probabilistic framework that disentangles physical affordance from semantic execution.
Outcome: The proposed framework disentangles physical affordance from semantic execution.
Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement (2025.findings-naacl)

Copied to clipboard

Challenge: Existing methods for visual and language alignment depend on external models or data, leading to uncontrollable and unstable results.
Approach: They propose a framework that enhances visual and language alignment without external dependencies by incorporating an in-context self-critic mechanism that constructs preference pairs for tuning.
Outcome: The proposed framework outperforms existing methods and improves performance on 14 hallucination and comprehensive benchmarks.
See-Saw Modality Balance: See Gradient, and Sew Impaired Vision-Language Balance to Mitigate Dominant Modality Bias (2025.naacl-long)

Copied to clipboard

Challenge: Vision-language models often rely on a single modality rather than treating and utilizing them equally, leading to dominance of a specific modality on the overall performance.
Approach: They propose a framework to mitigate dominant modality bias by adjusting the gradient of KL divergence based on each modality's contribution and aligning task directions in a non-conflicting manner.
Outcome: The proposed framework mitigates dominant modality bias on UPMC Food-101, Hateful Memes, and MM-IMDb datasets.
A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning (2022.aacl-main)

Copied to clipboard

Challenge: Large-scale, pretrained vision-language models are growing in popularity due to impressive performance on downstream tasks with minimal finetuning.
Approach: They propose to apply ranking metrics to image-text representations to investigate bias measures and debiasing methods to reduce various bias measures.
Outcome: The proposed model reduces bias measures with minimal degradation to image-text representations.
LVPruning: An Effective yet Simple Language-Guided Vision Token Pruning Approach for Multi-modal Large Language Models (2025.findings-naacl)

Copied to clipboard

Challenge: Multi-modal Large Language Models (MLLMs) incur significant computational overhead due to the large number of vision tokens processed, limiting their practicality in resource-constrained environments.
Approach: They propose a language-guided vision token pruning method that can be integrated into existing MLLMs with minimal architectural changes.
Outcome: The proposed method reduces vision tokens by 90% and preserves model performance.
Multi-Modal Bias: Introducing a Framework for Stereotypical Bias Assessment beyond Gender and Race in Vision–Language Models (2023.eacl-main)

Copied to clipboard

Challenge: Recent advances in self-supervised training have led to a new class of pretrained vision–language models.
Approach: They propose a visual and textual bias benchmark to assess bias in self-supervised multimodal models using 3,800 images and phrases from 14 population subgroups.
Outcome: The proposed model shows that it favors certain groups while maintaining the accuracy of the model.
BiasDora: Exploring Hidden Biased Associations in Vision-Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing studies on social biases focus on a limited set of documented associations, such as gender-profession or race-crime.
Approach: They propose to examine hidden, implicit bias associations across 9 bias dimensions by probing VLMs to uncover hidden, unexamined associations.
Outcome: The proposed methods reveal that biases vary in negativity, toxicity, and extremity.
ModSCAN: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities (2024.emnlp-main)

Copied to clipboard

Challenge: Large vision-language models have been widely used but stereotypical biases are unexplored.
Approach: They propose a framework to SCAN stereotypical bias within large vision-language models . they examine stereotype biases with respect to gender and race in three scenarios .
Outcome: The proposed framework can reduce stereotypical biases in large vision-language models . the currently popular models show significant stereotype biase .
Fairness Evaluation and Inference Level Mitigation in LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Large language models display undesirable behaviors embedded in their internal representations, undermining fairness, inconsistency drift, and the propagation of unwanted patterns during extended dialogues.
Approach: They propose a pruning-based framework that detects context-aware neuron activations and applies adaptive masking to modulate their influence during generation.
Outcome: The proposed framework detects context-aware neuron activations and applies adaptive masking to modulate their influence during generation.
Text Takes Over: A Study of Modality Bias in Multimodal Intent Detection (2025.emnlp-main)

Copied to clipboard

Challenge: a new study examines the effectiveness of large language models and non-LLMs in multimodal intent detection . large-scale multimodal data integrations include text, audio, and visual inputs .
Approach: They propose a framework to debias multimodal intent detection datasets by using human evaluation.
Outcome: The proposed framework debiases the datasets and shows that mistral-7B outperforms most competitive models by approximately 9% on MIntRec-1 and 4% on MIndRec2.0.

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