Cover Image

Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Nick, Kachinthaya, Anish, Petryk, Suzie, Gandelsman, Yossi
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ALOHa: A New Measure for Hallucination in Captioning Models
by: Petryk, Suzanne, et al.
Published: (2024)

Jailbreaking Vision-Language Models Through the Visual Modality
by: Azulay, Aharon, et al.
Published: (2026)

Vision Transformers Don't Need Trained Registers
by: Jiang, Nick, et al.
Published: (2025)

Interpreting the Weight Space of Customized Diffusion Models
by: Dravid, Amil, et al.
Published: (2024)

Interpreting ResNet-based CLIP via Neuron-Attention Decomposition
by: Bu, Edmund, et al.
Published: (2025)

Interpreting CLIP's Image Representation via Text-Based Decomposition
by: Gandelsman, Yossi, et al.
Published: (2023)

Learning Video Representations without Natural Videos
by: Yu, Xueyang, et al.
Published: (2024)

Look Closer! An Adversarial Parametric Editing Framework for Hallucination Mitigation in VLMs
by: Hu, Jiayu, et al.
Published: (2025)

Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression
by: Sarkar, Sreetama, et al.
Published: (2025)

HaloProbe: Bayesian Detection and Mitigation of Object Hallucinations in Vision-Language Models
by: Zohrabi, Reihaneh, et al.
Published: (2026)

Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
by: Zhou, Yiyang, et al.
Published: (2023)

Interpreting the Second-Order Effects of Neurons in CLIP
by: Gandelsman, Yossi, et al.
Published: (2024)

The Unreasonable Effectiveness of Text Embedding Interpolation for Continuous Image Steering
by: Ekin, Yigit, et al.
Published: (2026)

LLMs can see and hear without any training
by: Ashutosh, Kumar, et al.
Published: (2025)

Test-Time Training on Video Streams
by: Wang, Renhao, et al.
Published: (2023)

Efficient Contrastive Decoding with Probabilistic Hallucination Detection - Mitigating Hallucinations in Large Vision Language Models -
by: Fieback, Laura, et al.
Published: (2025)

Detecting and Preventing Hallucinations in Large Vision Language Models
by: Gunjal, Anisha, et al.
Published: (2023)

Mitigating Object Hallucinations in Vision-Language Models through Region-Aware Attention Recalibration
by: Xu, Yuanzhi, et al.
Published: (2026)

Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models
by: Tang, Kai, et al.
Published: (2025)

Retrieval Visual Contrastive Decoding to Mitigate Object Hallucinations in Large Vision-Language Models
by: Lee, Jihoon, et al.
Published: (2025)

Quantifying and Enabling the Interpretability of CLIP-like Models
by: Madasu, Avinash, et al.
Published: (2024)

Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback
by: Xiao, Wenyi, et al.
Published: (2024)

Online Self-Calibration Against Hallucination in Vision-Language Models
by: Chen, Minghui, et al.
Published: (2026)

Mitigating Diffusion Model Hallucinations with Dynamic Guidance
by: Triaridis, Kostas, et al.
Published: (2025)

Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance
by: Zhao, Linxi, et al.
Published: (2024)

HalluRNN: Mitigating Hallucinations via Recurrent Cross-Layer Reasoning in Large Vision-Language Models
by: Yu, Le, et al.
Published: (2025)

A Survey on Hallucination in Large Vision-Language Models
by: Liu, Hanchao, et al.
Published: (2024)

Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation
by: Li, Qiming, et al.
Published: (2025)

ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models
by: Park, Yeji, et al.
Published: (2024)

Interpreting Neurons in Deep Vision Networks with Language Models
by: Bai, Nicholas, et al.
Published: (2024)

Suppressing VLM Hallucinations with Spectral Representation Filtering
by: Ali, Ameen, et al.
Published: (2025)

Hallucination-Aware Multimodal Benchmark for Gastrointestinal Image Analysis with Large Vision-Language Models
by: Khanal, Bidur, et al.
Published: (2025)

What Makes "Good" Distractors for Object Hallucination Evaluation in Large Vision-Language Models?
by: Xie, Ming-Kun, et al.
Published: (2025)

Information Router for Mitigating Modality Dominance in Vision-Language Models
by: Kim, Seulgi, et al.
Published: (2026)

Multilingual Diversity Improves Vision-Language Representations
by: Nguyen, Thao, et al.
Published: (2024)

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding
by: Tang, Feilong, et al.
Published: (2025)

Locate-then-Sparsify: Attribution Guided Sparse Strategy for Visual Hallucination Mitigation
by: Dang, Tiantian, et al.
Published: (2026)

Overconfidence and Calibration in Medical VQA: Empirical Findings and Hallucination-Aware Mitigation
by: Byun, Ji Young, et al.
Published: (2026)

RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models
by: Zhang, Serena, et al.
Published: (2024)

Towards Interpreting Visual Information Processing in Vision-Language Models
by: Neo, Clement, et al.
Published: (2024)