English
Related papers

Related papers: Using Hallucinations to Bypass GPT4's Filter

200 papers

Learning from human feedback is a prominent technique to align the output of large language models (LLMs) with human expectations. Reinforcement learning from human feedback (RLHF) leverages human preference signals that are in the form of…

Computation and Language · Computer Science 2023-11-27 Di Jin , Shikib Mehri , Devamanyu Hazarika , Aishwarya Padmakumar , Sungjin Lee , Yang Liu , Mahdi Namazifar

Large Vision-Language Models (LVLMs) have demonstrated impressive multimodal understanding capabilities, yet they remain prone to object hallucination, where models describe non-existent objects or attribute incorrect factual information,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Ahmed Akl , Abdelwahed Khamis , Ali Cheraghian , Zhe Wang , Sara Khalifa , Kewen Wang

Since the introduction of ChatGPT, large language models (LLMs) have demonstrated significant utility in various tasks, such as answering questions through retrieval-augmented generation. Context can be retrieved using a vectorized…

Computation and Language · Computer Science 2025-07-01 Ming Cheung

Prior works have shown that fine-tuning on new knowledge can induce factual hallucinations in large language models (LLMs), leading to incorrect outputs when evaluated on previously known information. However, the specific manifestations of…

Computation and Language · Computer Science 2026-04-20 Renfei Dang , Peng Hu , Zhejian Lai , Changjiang Gao , Min Zhang , Shujian Huang

Large Language Models (LLMs) have demonstrated exceptional performance across various natural language processing tasks. However, they occasionally generate inaccurate and counterfactual outputs, a phenomenon commonly referred to as…

Computation and Language · Computer Science 2025-06-04 Dingwei Chen , Feiteng Fang , Shiwen Ni , Feng Liang , Xiping Hu , Ahmadreza Argha , Hamid Alinejad-Rokny , Min Yang , Chengming Li

Large language models (LLMs) now achieve near-human performance on standard math word problem benchmarks (e.g., GSM8K), yet their true reasoning ability remains disputed. A key concern is that models often produce confident, yet unfounded,…

Computation and Language · Computer Science 2025-05-21 Jialin Ouyang

Timely and effective incident response is key to managing the growing frequency of cyberattacks. However, identifying the right response actions for complex systems is a major technical challenge. A promising approach to mitigate this…

Cryptography and Security · Computer Science 2025-08-08 Kim Hammar , Tansu Alpcan , Emil C. Lupu

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

The questionable responses caused by knowledge hallucination may lead to LLMs' unstable ability in decision-making. However, it has never been investigated whether the LLMs' hallucination is possibly usable to generate negative reasoning…

Computation and Language · Computer Science 2025-03-13 Chaowei Zhang , Zongling Feng , Zewei Zhang , Jipeng Qiang , Guandong Xu , Yun Li

Large language models (LLMs) have achieved remarkable advancements in natural language processing. However, the massive scale and computational demands of these models present formidable challenges when considering their practical…

Computation and Language · Computer Science 2024-04-09 Weize Liu , Guocong Li , Kai Zhang , Bang Du , Qiyuan Chen , Xuming Hu , Hongxia Xu , Jintai Chen , Jian Wu

Fusing visual understanding into language generation, Multi-modal Large Language Models (MLLMs) are revolutionizing visual-language applications. Yet, these models are often plagued by the hallucination problem, which involves generating…

Machine Learning · Computer Science 2025-01-28 Yining Wang , Mi Zhang , Junjie Sun , Chenyue Wang , Min Yang , Hui Xue , Jialing Tao , Ranjie Duan , Jiexi Liu

Vision-Language Models (VLMs) excel at visual understanding but often suffer from visual hallucinations, where they generate descriptions of nonexistent objects, actions, or concepts, posing significant risks in safety-critical…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Tsung-Han Wu , Heekyung Lee , Jiaxin Ge , Joseph E. Gonzalez , Trevor Darrell , David M. Chan

Self-improvement in multimodal large language models (MLLMs) is crucial for enhancing their reliability and robustness. However, current methods often rely heavily on MLLMs themselves as judges, leading to high computational costs and…

Computation and Language · Computer Science 2024-11-28 Shijian Deng , Wentian Zhao , Yu-Jhe Li , Kun Wan , Daniel Miranda , Ajinkya Kale , Yapeng Tian

Aligning large language models (LLMs) with human preferences is crucial for enhancing their utility in terms of helpfulness, truthfulness, safety, harmlessness, and interestingness. Existing methods for achieving this alignment often…

Computation and Language · Computer Science 2024-07-04 Wenhao Liu , Xiaohua Wang , Muling Wu , Tianlong Li , Changze Lv , Zixuan Ling , Jianhao Zhu , Cenyuan Zhang , Xiaoqing Zheng , Xuanjing Huang

The fluency and creativity of large pre-trained language models (LLMs) have led to their widespread use, sometimes even as a replacement for traditional search engines. Yet language models are prone to making convincing but factually…

Computation and Language · Computer Science 2023-11-15 Katherine Tian , Eric Mitchell , Huaxiu Yao , Christopher D. Manning , Chelsea Finn

Reinforcement Learning from Human Feedback (RLHF) has shown remarkable success in aligning Large Language Models (LLMs) with human preferences. Traditional RLHF methods rely on a fixed dataset, which often suffers from limited coverage. To…

Machine Learning · Computer Science 2025-10-28 Long-Fei Li , Yu-Yang Qian , Peng Zhao , Zhi-Hua Zhou

Large Vision-Language Models (LVLMs) have demonstrated proficiency in tackling a variety of visual-language tasks. However, current LVLMs suffer from misalignment between text and image modalities which causes three kinds of hallucination…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 Liqiang Jing , Xinya Du

Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP). Although convenient for research and practical applications, open-source LLMs with fewer parameters often suffer from severe hallucinations compared to…

Computation and Language · Computer Science 2023-09-15 Mohamed Elaraby , Mengyin Lu , Jacob Dunn , Xueying Zhang , Yu Wang , Shizhu Liu , Pingchuan Tian , Yuping Wang , Yuxuan Wang

When large language models are aligned via supervised fine-tuning, they may encounter new factual information that was not acquired through pre-training. It is often conjectured that this can teach the model the behavior of hallucinating…

Computation and Language · Computer Science 2024-10-02 Zorik Gekhman , Gal Yona , Roee Aharoni , Matan Eyal , Amir Feder , Roi Reichart , Jonathan Herzig

Large Language Models with transformer architecture have revolutionized the domain of text generation, setting unprecedented benchmarks. Despite their impressive capabilities, LLMs have been criticized for generating outcomes that deviate…

Computation and Language · Computer Science 2024-02-22 Aline Ioste
‹ Prev 1 8 9 10 Next ›