English
Related papers

Related papers: SECA: Semantically Equivalent and Coherent Attacks…

200 papers

Large Vision-Language Models (LVLMs) have demonstrated remarkable performance in complex multimodal tasks. However, these models still suffer from hallucinations, particularly when required to implicitly recognize or infer diverse visual…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Ashish Seth , Dinesh Manocha , Chirag Agarwal

Large Language Models (LLMs) have gained significant popularity for their impressive performance across diverse fields. However, LLMs are prone to hallucinate untruthful or nonsensical outputs that fail to meet user expectations in many…

Computation and Language · Computer Science 2023-11-23 Tianhang Zhang , Lin Qiu , Qipeng Guo , Cheng Deng , Yue Zhang , Zheng Zhang , Chenghu Zhou , Xinbing Wang , Luoyi Fu

As Large Language Models (LLMs) are increasingly being deployed in safety-critical applications, their vulnerability to potential jailbreaks -- malicious prompts that can disable the safety mechanism of LLMs -- has attracted growing…

Cryptography and Security · Computer Science 2024-08-08 Jiahao Zhang , Zilong Wang , Ruofan Wang , Xingjun Ma , Yu-Gang Jiang

Hallucinations pose a significant challenge to the reliability and alignment of Large Language Models (LLMs), limiting their widespread acceptance beyond chatbot applications. Despite ongoing efforts, hallucinations remain a prevalent…

Computation and Language · Computer Science 2024-02-27 Cem Uluoglakci , Tugba Taskaya Temizel

Despite remarkable advancements in mitigating hallucinations in large language models (LLMs) by retrieval augmentation, it remains challenging to measure the reliability of LLMs using static question-answering (QA) data. Specifically, given…

Computation and Language · Computer Science 2024-06-04 Xiaodong Yu , Hao Cheng , Xiaodong Liu , Dan Roth , Jianfeng Gao

Multimodal large language models (MLLMs) have revolutionized cross-modal understanding but continue to struggle with hallucinations - fabricated content contradicting visual inputs. Existing hallucination mitigation methods either incur…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Shangpin Peng , Senqiao Yang , Li Jiang , Zhuotao Tian

As the integration of the Large Language Models (LLMs) into various applications increases, so does their susceptibility to misuse, raising significant security concerns. Numerous jailbreak attacks have been proposed to assess the security…

Cryptography and Security · Computer Science 2025-05-30 Bijoy Ahmed Saiem , MD Sadik Hossain Shanto , Rakib Ahsan , Md Rafi ur Rashid

Large language models (LLMs) are susceptible to generating hallucinated information, despite the integration of retrieval-augmented generation (RAG). Parallel context extension (PCE) is a line of research attempting to effectively…

Computation and Language · Computer Science 2024-12-20 Zexiong Ma , Shengnan An , Zeqi Lin , Yanzhen Zou , Jian-Guang Lou , Bing Xie

The deployment of large language models (LLMs) has raised security concerns due to their susceptibility to producing harmful or policy-violating outputs when exposed to adversarial prompts. While alignment and guardrails mitigate common…

Computation and Language · Computer Science 2026-01-23 Rishit Chugh

In contemporary software development, the widespread use of indirect calls to achieve dynamic features poses challenges in constructing precise control flow graphs (CFGs), which further impacts the performance of downstream static analysis…

Software Engineering · Computer Science 2024-11-01 Baijun Cheng , Cen Zhang , Kailong Wang , Ling Shi , Yang Liu , Haoyu Wang , Yao Guo , Ding Li , Xiangqun Chen

Hallucinations in Large Language Models (LLMs), i.e., the tendency to generate plausible but non-factual content, pose a significant challenge for their reliable deployment in high-stakes environments. However, existing hallucination…

Computation and Language · Computer Science 2026-01-29 Yitong Qiao , Licheng Pan , Yu Mi , Lei Liu , Yue Shen , Fei Sun , Zhixuan Chu

The development of Large Language Models (LLMs) has significantly advanced various AI applications in commercial and scientific research fields, such as scientific literature summarization, writing assistance, and knowledge graph…

Computation and Language · Computer Science 2024-10-17 Huiwen Wu , Xiaohan Li , Xiaogang Xu , Jiafei Wu , Deyi Zhang , Zhe Liu

Large Language Models (LLMs) demonstrate remarkable capabilities in leveraging comprehensive world knowledge and sophisticated reasoning mechanisms for recommendation tasks. However, a notable limitation lies in their inability to…

Information Retrieval · Computer Science 2025-04-15 Zihan Wang , Jinghao Lin , Xiaocui Yang , Yongkang Liu , Shi Feng , Daling Wang , Yifei Zhang

In the era of large language models (LLMs), hallucination (i.e., the tendency to generate factually incorrect content) poses great challenge to trustworthy and reliable deployment of LLMs in real-world applications. To tackle the LLM…

Computation and Language · Computer Science 2024-01-09 Junyi Li , Jie Chen , Ruiyang Ren , Xiaoxue Cheng , Wayne Xin Zhao , Jian-Yun Nie , Ji-Rong Wen

Recent studies have shown that Vision Language Large Models (VLLMs) may output content not relevant to the input images. This problem, called the hallucination phenomenon, undoubtedly degrades VLLM performance. Therefore, various…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Minyi Zhao , Jie Wang , Zhaoyang Li , Jiyuan Zhang , Zhenbang Sun , Shuigeng Zhou

LLMs deployed in high-stakes domains face fundamental reliability challenges: hallucinations, inconsistencies, and privacy vulnerabilities introduce unacceptable risks where errors carry legal, financial, or safety consequences. This paper…

Artificial Intelligence · Computer Science 2026-05-27 Paul Sigloch , Christoph Benzmüller

Large language models (LLMs) are increasingly deployed across diverse domains, yet they are prone to generating factually incorrect outputs - commonly known as "hallucinations." Among existing mitigation strategies, uncertainty-based…

Computation and Language · Computer Science 2025-03-11 Samir Abdaljalil , Hasan Kurban , Parichit Sharma , Erchin Serpedin , Rachad Atat

To prevent Text-to-Image (T2I) models from generating unethical images, people deploy safety filters to block inappropriate drawing prompts. Previous works have employed token replacement to search adversarial prompts that attempt to bypass…

Artificial Intelligence · Computer Science 2024-11-27 Yimo Deng , Huangxun Chen

Harmful fine-tuning attacks pose a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment,…

Machine Learning · Computer Science 2026-03-03 Yuhui Wang , Rongyi Zhu , Ting Wang

Automatic adversarial prompt generation provides remarkable success in jailbreaking safely-aligned large language models (LLMs). Existing gradient-based attacks, while demonstrating outstanding performance in jailbreaking white-box LLMs,…

Machine Learning · Computer Science 2025-01-22 Qizhang Li , Xiaochen Yang , Wangmeng Zuo , Yiwen Guo
‹ Prev 1 3 4 5 6 7 10 Next ›