Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations

3 October 2024

Papers citing "Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations"

8 / 8 papers shown

Title
VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations for Synthetic Videos Zongxia Li Xiyang Wu Yubin Qin Guangyao Shi Hongyang Du Dinesh Manocha Tianyi Zhou Jordan Boyd-Graber MLLM 41 0 0 02 May 2025
Treble Counterfactual VLMs: A Causal Approach to Hallucination Li Li Jiashu Qu Yuxiao Zhou Yuehan Qin Tiankai Yang Yue Zhao 78 1 0 08 Mar 2025
Forgotten Polygons: Multimodal Large Language Models are Shape-Blind William Rudman Michal Golovanesky Amir Bar Vedant Palit Yann LeCun Carsten Eickhoff Ritambhara Singh LRM 47 2 0 21 Feb 2025
SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders Bartosz Cywiñski Kamil Deja DiffM 61 6 0 29 Jan 2025
Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Zhangqi Jiang Junkai Chen Beier Zhu Tingjin Luo Yankun Shen Xu Yang 95 4 0 23 Nov 2024
Towards Interpreting Visual Information Processing in Vision-Language Models Clement Neo Luke Ong Philip H. S. Torr Mor Geva David M. Krueger Fazl Barez 84 6 0 09 Oct 2024
What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation Michal Golovanevsky William Rudman Vedant Palit Ritambhara Singh Carsten Eickhoff 29 1 0 24 Jun 2024
Hallucination of Multimodal Large Language Models: A Survey Zechen Bai Pichao Wang Tianjun Xiao Tong He Zongbo Han Zheng Zhang Mike Zheng Shou VLM LRM 80 139 0 29 Apr 2024