English
Related papers

Related papers: Automated Multi-level Preference for MLLMs

200 papers

Recently, there has been significant interest in replacing the reward model in Reinforcement Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs), such as Direct Preference Optimization (DPO) and its variants. These…

Computation and Language · Computer Science 2024-09-27 Jian Li , Haojing Huang , Yujia Zhang , Pengfei Xu , Xi Chen , Rui Song , Lida Shi , Jingwen Wang , Hao Xu

Hallucination remains a fundamental challenge in vision-language models (VLMs), where autoregressive generation may produce linguistically plausible yet physically inconsistent or visually ungrounded responses due to likelihood maximization…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Qinwu Xu

Reinforcement learning from human feedback (RLHF) has emerged as the primary method for aligning large language models (LLMs) with human preferences. The RLHF process typically starts by training a reward model (RM) using human preference…

Machine Learning · Computer Science 2024-06-19 Haoxiang Wang , Wei Xiong , Tengyang Xie , Han Zhao , Tong Zhang

The emergence of large Vision Language Models (VLMs) has broadened the scope and capabilities of single-modal Large Language Models (LLMs) by integrating visual modalities, thereby unlocking transformative cross-modal applications in a…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Shuo Xing , Peiran Li , Yuping Wang , Ruizheng Bai , Yueqi Wang , Chan-Wei Hu , Chengxuan Qian , Huaxiu Yao , Zhengzhong Tu

Multi-modal large language models (MLLMs) have been shown to efficiently integrate natural language with visual information to handle multi-modal tasks. However, MLLMs still face a fundamental limitation of hallucinations, where they tend…

Computer Vision and Pattern Recognition · Computer Science 2024-02-27 Chaoya Jiang , Haiyang Xu , Mengfan Dong , Jiaxing Chen , Wei Ye , Ming Yan , Qinghao Ye , Ji Zhang , Fei Huang , Shikun Zhang

Multimodal Large Language Models (MLLMs) frequently suffer from hallucination issues, generating information about objects that are not present in input images during vision-language tasks. These hallucinations particularly undermine model…

Computer Vision and Pattern Recognition · Computer Science 2025-06-16 Dokyoon Yoon , Youngsook Song , Woomyong Park

Multimodal Large Language Models (MLLMs) still struggle with hallucinations despite their impressive capabilities. Recent studies have attempted to mitigate this by applying Direct Preference Optimization (DPO) to multimodal scenarios using…

Computation and Language · Computer Science 2025-01-29 Jinlan Fu , Shenzhen Huangfu , Hao Fei , Xiaoyu Shen , Bryan Hooi , Xipeng Qiu , See-Kiong Ng

Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm in artificial intelligence to align large models with human preferences. In this paper, we propose a novel statistical framework to simultaneously conduct the…

Machine Learning · Statistics 2026-05-01 Nan Lu , Ethan Lee , Ethan X. Fang , Junwei Lu

Multi-modal Large Language Models (MLLMs) excel at single-image tasks but struggle with multi-image understanding due to cross-modal misalignment, leading to hallucinations (context omission, conflation, and misinterpretation). Existing…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Xudong Li , Mengdan Zhang , Peixian Chen , Xiawu Zheng , Yan Zhang , Jingyuan Zheng , Yunhang Shen , Ke Li , Chaoyou Fu , Xing Sun , Rongrong Ji

Aligning large language models (LLMs) with human preferences has become essential for safe and beneficial AI deployment. While Reinforcement Learning from Human Feedback (RLHF) established the dominant paradigm, a proliferation of…

Artificial Intelligence · Computer Science 2026-01-13 Tarun Raheja , Nilay Pochhi

The task adaptation and alignment of Large Multimodal Models (LMMs) have been significantly advanced by instruction tuning and further strengthened by recent preference optimization. Yet, most LMMs still suffer from severe modality…

Machine Learning · Computer Science 2025-10-10 Chenxi Liu , Tianyi Xiong , Yanshuo Chen , Ruibo Chen , Yihan Wu , Junfeng Guo , Tianyi Zhou , Heng Huang

Medical Large Language Models (MLLMs) have demonstrated potential in healthcare applications, yet their propensity for hallucinations -- generating medically implausible or inaccurate information -- presents substantial risks to patient…

Computation and Language · Computer Science 2025-04-01 Kaiwen Zuo , Yirui Jiang

Despite recent successes, LVLMs or Large Vision Language Models are prone to hallucinating details like objects and their properties or relations, limiting their real-world deployment. To address this and improve their robustness, we…

Computer Vision and Pattern Recognition · Computer Science 2024-08-21 Yassine Ouali , Adrian Bulat , Brais Martinez , Georgios Tzimiropoulos

Reinforcement Learning from Human Feedback (RLHF) is the standard method to align Large Language Models (LLMs) with human preferences. In this work, we introduce alignment tampering, a potential vulnerability where the LLM undergoing…

Artificial Intelligence · Computer Science 2026-05-27 Dongyoon Hahm , Dylan Hadfield-Menell , Kimin Lee

The rapidly developing Large Vision Language Models (LVLMs) have shown notable capabilities on a range of multi-modal tasks, but still face the hallucination phenomena where the generated texts do not align with the given contexts,…

Computer Vision and Pattern Recognition · Computer Science 2025-01-07 Wenyi Xiao , Ziwei Huang , Leilei Gan , Wanggui He , Haoyuan Li , Zhelun Yu , Fangxun Shu , Hao Jiang , Linchao Zhu

While Large Vision-Language Models (LVLMs) have exhibited remarkable capabilities across a wide range of tasks, they suffer from hallucination problems, where models generate plausible yet incorrect answers given the input image-query pair.…

Computer Vision and Pattern Recognition · Computer Science 2024-08-02 Xiaoye Qu , Mingyang Song , Wei Wei , Jianfeng Dong , Yu Cheng

Reinforcement learning from human feedback (RLHF) has emerged as the primary method for aligning large language models (LLMs) with human preferences. While it enables LLMs to achieve human-level alignment, it often incurs significant…

Computation and Language · Computer Science 2025-03-21 Shivank Garg , Ayush Singh , Shweta Singh , Paras Chopra

Although large vision-language models (LVLMs) have demonstrated remarkable capabilities, they are prone to hallucinations in multi-image tasks. We attribute this issue to limitations in existing attention mechanisms and insufficient…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Xiaochen Yang , Hao Fang , Jiawei Kong , Yaoxin Mao , Bin Chen , Shu-Tao Xia

Mathematical reasoning is a fundamental capability for large language models (LLMs), yet achieving high performance in this domain remains a significant challenge. The auto-regressive generation process often makes LLMs susceptible to…

Artificial Intelligence · Computer Science 2024-12-02 Xiaoxuan Lou , Chaojie Wang , Bo An

Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal tool for aligning large language models (LLMs) with human preferences. Direct Preference Optimization (DPO), one of the most popular approaches, formulates RLHF as a…

Machine Learning · Computer Science 2024-10-10 Jiafan He , Huizhuo Yuan , Quanquan Gu