English
Related papers

Related papers: Steering LVLMs via Sparse Autoencoder for Hallucin…

200 papers

Large Vision-Language Models (LVLMs) have shown remarkable performance on many visual-language tasks. However, these models still suffer from multimodal hallucination, which means the generation of objects or content that violates the…

Computation and Language · Computer Science 2024-10-01 Fan Yuan , Chi Qin , Xiaogang Xu , Piji Li

While large vision-language models (LVLMs) have shown impressive capabilities in generating plausible responses correlated with input visual contents, they still suffer from hallucinations, where the generated text inaccurately reflects…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Yi-Lun Lee , Yi-Hsuan Tsai , Wei-Chen Chiu

Vision-Language Models (VLMs) have shown solid ability for multimodal understanding of both visual and language contexts. However, existing VLMs often face severe challenges of hallucinations, meaning that VLMs tend to generate responses…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Jinjin Cao , Zhiyang Chen , Zijun Wang , Liyuan Ma , Weijian Luo , Guojun Qi

Large Vision-Language Models (LVLMs) have achieved substantial progress in cross-modal tasks. However, due to language bias, LVLMs are susceptible to object hallucination, which can be primarily divided into category, attribute, and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Tianbo Wang , Yuqing Ma , Kewei Liao , Zhange Zhang , Simin Li , Jinyang Guo , Xianglong Liu

Despite their success, Large Vision-Language Models (LVLMs) remain vulnerable to hallucinations. While existing studies attribute the cause of hallucinations to insufficient visual attention to image tokens, our findings indicate that…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Beitao Chen , Xinyu Lyu , Lianli Gao , Jingkuan Song , Heng Tao Shen

Vision-language models (VLMs) frequently generate hallucinated content plausible but incorrect claims about image content. We propose a training-free self-correction framework enabling VLMs to iteratively refine responses through…

Computer Vision and Pattern Recognition · Computer Science 2025-12-11 Kassoum Sanogo , Renzo Ardiccioni

Large Language Models (LLMs) are traditionally viewed as black-box algorithms, therefore reducing trustworthiness and obscuring potential approaches to increasing performance on downstream tasks. In this work, we apply an effective LLM…

Computation and Language · Computer Science 2025-07-10 Shun Wang , Tyler Loakman , Youbo Lei , Yi Liu , Bohao Yang , Yuting Zhao , Dong Yang , Chenghua Lin

Large Vision-Language Models (LVLMs) are susceptible to hallucinations, where generated responses seem semantically plausible yet exhibit little or no relevance to the input image. Previous studies reveal that this issue primarily stems…

Computation and Language · Computer Science 2025-10-24 Hao Fang , Changle Zhou , Jiawei Kong , Kuofeng Gao , Bin Chen , Shu-Tao Xia

Large Vision-Language Models (LVLMs) have recently achieved remarkable success. However, LVLMs are still plagued by the hallucination problem, which limits the practicality in many scenarios. Hallucination refers to the information of…

Machine Learning · Computer Science 2023-10-11 Junyang Wang , Yiyang Zhou , Guohai Xu , Pengcheng Shi , Chenlin Zhao , Haiyang Xu , Qinghao Ye , Ming Yan , Ji Zhang , Jihua Zhu , Jitao Sang , Haoyu Tang

Large vision-language models (LVLMs) have demonstrated exceptional performance on complex multimodal tasks. However, they continue to suffer from significant hallucination issues, including object, attribute, and relational hallucinations.…

Computer Vision and Pattern Recognition · Computer Science 2025-08-01 Yudong Zhang , Ruobing Xie , Xingwu Sun , Yiqing Huang , Jiansheng Chen , Zhanhui Kang , Di Wang , Yu Wang

Prompt-based verification is widely used to mitigate hallucinations in large vision-language models (LVLMs), yet when it helps remains poorly understood. We systematically study verification prompting across two representative LVLM…

Computation and Language · Computer Science 2026-05-28 Yuang Huang , Yafeng Zhang , Yu Zilan

Fine-grained steering of language model outputs is essential for safety and reliability. Prompting and finetuning are widely used to achieve these goals, but interpretability researchers have proposed a variety of representation-based…

Computation and Language · Computer Science 2025-03-05 Zhengxuan Wu , Aryaman Arora , Atticus Geiger , Zheng Wang , Jing Huang , Dan Jurafsky , Christopher D. Manning , Christopher Potts

Large language models (LLMs) are growingly extended to process multimodal data such as text and video simultaneously. Their remarkable performance in understanding what is shown in images is surpassing specialized neural networks (NNs) such…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Malsha Ashani Mahawatta Dona , Beatriz Cabrero-Daniel , Yinan Yu , Christian Berger

Recently, Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in multi-modal context comprehension. However, they still suffer from hallucination problems referring to generating inconsistent outputs with the…

Computer Vision and Pattern Recognition · Computer Science 2024-09-02 Xiaoye Qu , Jiashuo Sun , Wei Wei , Yu Cheng

Sparse autoencoders (SAEs) are increasingly used to extract activation directions for inference-time steering, but their standard sparsity objective treats latent features as independent. This prior can be poorly matched to high-level…

Machine Learning · Computer Science 2026-05-18 Jehyeok Yeon , Federico Cinus , Yifan Wu , Luca Luceri

Large Vision-Language Models (LVLMs) are increasingly adept at generating contextually detailed and coherent responses from visual inputs. However, their application in multimodal decision-making and open-ended generation is hindered by a…

Computer Vision and Pattern Recognition · Computer Science 2024-06-06 Xintong Wang , Jingheng Pan , Liang Ding , Chris Biemann

While vision models are highly capable, their internal mechanisms remain poorly understood -- a challenge which sparse autoencoders (SAEs) have helped address in language, but which remains underexplored in vision. We address this gap by…

Computer Vision and Pattern Recognition · Computer Science 2025-04-14 Sonia Joseph , Praneet Suresh , Ethan Goldfarb , Lorenz Hufe , Yossi Gandelsman , Robert Graham , Danilo Bzdok , Wojciech Samek , Blake Aaron Richards

Large language models (LLMs) demonstrate exceptional performance on tasks requiring complex linguistic abilities, such as reference disambiguation and metaphor recognition/generation. Although LLMs possess impressive capabilities, their…

Computation and Language · Computer Science 2025-09-16 Yi Jing , Zijun Yao , Hongzhu Guo , Lingxu Ran , Xiaozhi Wang , Lei Hou , Juanzi Li

Large vision-language models (LVLMs) often hallucinate when language priors dominate weak or ambiguous visual evidence. Existing contrastive decoding methods mitigate this problem by comparing predictions from the original image with those…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Tian Qin , Junzhe Chen , Yuqing Shi , Tianshu Zhang , Qiang Ju , Lijie Wen

Large Language Models (LLMs) frequently exhibit strong translation abilities, even without task-specific fine-tuning. However, the internal mechanisms governing this innate capability remain largely opaque. To demystify this process, we…

Computation and Language · Computer Science 2026-01-19 Xinwei Wu , Heng Liu , Xiaohu Zhao , Yuqi Ren , Linlong Xu , Longyue Wang , Deyi Xiong , Weihua Luo , Kaifu Zhang