Cover Image

Debiasing CLIP: Interpreting and Correcting Bias in Attention Heads

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yeo, Wei Jie, Mao, Rui, Abdar, Moloud, Cambria, Erik, Satapathy, Ranjan
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models
by: Yeo, Wei Jie, et al.
Published: (2024)

Plausible Extractive Rationalization through Semi-Supervised Entailment Signal
by: Yeo, Wei Jie, et al.
Published: (2024)

Unknown Prompt, the only Lacuna: Unveiling CLIP's Potential for Open Domain Generalization
by: Singha, Mainak, et al.
Published: (2024)

Mitigating Jailbreaks with Intent-Aware LLMs
by: Yeo, Wei Jie, et al.
Published: (2025)

How Interpretable are Reasoning Explanations from Prompting Large Language Models?
by: Yeo, Wei Jie, et al.
Published: (2024)

FOCUS: Bridging Fine-Grained Recognition and Open-World Discovery across Domains
by: Rathore, Vaibhav, et al.
Published: (2026)

Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP
by: Zhang, Zeliang, et al.
Published: (2024)

Is CLIP Cross-Eyed? Revealing and Mitigating Center Bias in the CLIP Family
by: Chew, Oscar, et al.
Published: (2026)

ATR-Bench: A Federated Learning Benchmark for Adaptation, Trust, and Reasoning
by: Ashraf, Tajamul, et al.
Published: (2025)

Towards Multimodal Sentiment Analysis Debiasing via Bias Purification
by: Yang, Dingkang, et al.
Published: (2024)

Self-training Large Language Models through Knowledge Detection
by: Yeo, Wei Jie, et al.
Published: (2024)

Locating Demographic Bias at the Attention-Head Level in CLIP's Vision Encoder
by: Yasser, Alaa, et al.
Published: (2026)

EduStory: A Unified Framework for Pedagogically-Consistent Multi-Shot STEM Instructional Video Generation
by: Wu, Xinyi, et al.
Published: (2026)

CLIP-SVD: Efficient and Interpretable Vision-Language Adaptation via Singular Values
by: Koleilat, Taha, et al.
Published: (2025)

FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models
by: Singha, Mainak, et al.
Published: (2025)

Improving Alignment in LVLMs with Debiased Self-Judgment
by: Yang, Sihan, et al.
Published: (2025)

BayTTA: Uncertainty-aware medical image classification with optimized test-time augmentation using Bayesian model averaging
by: Sherkatghanad, Zeinab, et al.
Published: (2024)

GroundedSurg: A Multi-Procedure Benchmark for Language-Conditioned Surgical Tool Segmentation
by: Ashraf, Tajamul, et al.
Published: (2026)

QTrack: Query-Driven Reasoning for Multi-modal MOT
by: Ashraf, Tajamul, et al.
Published: (2026)

Investigating Spatial Attention Bias in Vision-Language Models
by: Chaudhary, Aryan, et al.
Published: (2025)

Acceleration Multiple Heads Decoding for LLM via Dynamic Tree Attention
by: Zhang, Zhendong
Published: (2025)

Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP
by: Kim, Eunji, et al.
Published: (2024)

Owls are wise and foxes are unfaithful: Uncovering animal stereotypes in vision-language models
by: Aman, Tabinda, et al.
Published: (2025)

AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning
by: Tang, Yuwei, et al.
Published: (2024)

Demystifying CLIP Data
by: Xu, Hu, et al.
Published: (2023)

Optimizing Multimodal Language Models through Attention-based Interpretability
by: Sergeev, Alexander, et al.
Published: (2025)

Modality Bias in LVLMs: Analyzing and Mitigating Object Hallucination via Attention Lens
by: Zheng, Haohan, et al.
Published: (2025)

CultureCLIP: Empowering CLIP with Cultural Awareness through Synthetic Images and Contextualized Captions
by: Huang, Yuchen, et al.
Published: (2025)

TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives
by: Patel, Maitreya, et al.
Published: (2024)

Multi-Head Attention Driven Dynamic Visual-Semantic Embedding for Enhanced Image-Text Matching
by: Chen, Wenjing
Published: (2024)

LowCLIP: Adapting the CLIP Model Architecture for Low-Resource Languages in Multimodal Image Retrieval Task
by: Asgarov, Ali, et al.
Published: (2024)

FLEX-CLIP: Feature-Level GEneration Network Enhanced CLIP for X-shot Cross-modal Retrieval
by: Xie, Jingyou, et al.
Published: (2024)

Recurrent Visual Feature Extraction and Stereo Attentions for CT Report Generation
by: Tian, Yuanhe, et al.
Published: (2025)

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
by: Mao, Weian, et al.
Published: (2026)

Head Pursuit: Probing Attention Specialization in Multimodal Transformers
by: Basile, Lorenzo, et al.
Published: (2025)

Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization
by: Zhang, Zefeng, et al.
Published: (2025)

VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models
by: Wang, Jiapeng, et al.
Published: (2024)

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing
by: Xing, Long, et al.
Published: (2025)

Meta CLIP 2: A Worldwide Scaling Recipe
by: Chuang, Yung-Sung, et al.
Published: (2025)

Generalizable Prompt Learning of CLIP: A Brief Overview
by: Cui, Fangming, et al.
Published: (2025)