中文
相关论文

相关论文: Detecting LLM Hallucinations via Embedding Cluster…

200 篇论文

Large language models (LLMs) frequently generate confident yet inaccurate responses, introducing significant risks for deployment in safety-critical domains. We present a novel, test-time approach to detecting model hallucination through…

机器学习 · 计算机科学 2025-10-07 Hazel Kim , Tom A. Lamb , Adel Bibi , Philip Torr , Yarin Gal

Despite their impressive performance across a wide range of tasks, Large Vision-Language Models (LVLMs) remain prone to hallucination. In this study, we propose a comprehensive intervention framework aligned with the transformer's causal…

计算机视觉与模式识别 · 计算机科学 2026-01-07 Jiaye Qian , Ge Zheng , Yuchen Zhu , Sibei Yang

Hallucinations in large language models (LLMs) have recently become a significant problem. A recent effort in this direction is a shared task at Semeval 2024 Task 6, SHROOM, a Shared-task on Hallucinations and Related Observable…

计算与语言 · 计算机科学 2024-04-12 Rahul Mehta , Andrew Hoblitzell , Jack O'Keefe , Hyeju Jang , Vasudeva Varma

In Text-to-SQL generation, large language models (LLMs) have shown strong generalization and adaptability. However, LLMs sometimes generate hallucinations, i.e.,unrealistic or illogical content, which leads to incorrect SQL queries and…

软件工程 · 计算机科学 2025-12-30 Bo Yang , Yinfen Xia , Weisong Sun , Yang Liu

Recent advancements in massively multilingual machine translation systems have significantly enhanced translation accuracy; however, even the best performing systems still generate hallucinations, severely impacting user trust. Detecting…

Large language models (LLMs), including ChatGPT, Bard, and Llama, have achieved remarkable successes over the last two years in a range of different applications. In spite of these successes, there exist concerns that limit the wide…

计算与语言 · 计算机科学 2024-01-17 Junliang Luo , Tianyu Li , Di Wu , Michael Jenkin , Steve Liu , Gregory Dudek

We propose an auditing method to identify whether a large language model (LLM) encodes patterns such as hallucinations in its internal states, which may propagate to downstream tasks. We introduce a weakly supervised auditing technique…

机器学习 · 计算机科学 2023-12-06 Miriam Rateike , Celia Cintas , John Wamburu , Tanya Akumu , Skyler Speakman

Multi-modal Large Language Models (MLLMs) have emerged as a powerful paradigm for integrating visual and textual information, supporting a wide range of multi-modal tasks. However, these models often suffer from hallucination, producing…

计算机视觉与模式识别 · 计算机科学 2026-01-13 Zhiyuan Chen , Yuecong Min , Jie Zhang , Bei Yan , Jiahao Wang , Xiaozhen Wang , Shiguang Shan

Large language models (LLMs) hallucinate: they produce fluent outputs that are factually incorrect. We present a geometric dynamical systems framework in which hallucinations arise from task-dependent basin structure in latent space. Using…

计算与语言 · 计算机科学 2026-04-07 Kalyan Cherukuri , Lav R. Varshney

We show that language models hallucinate not because they fail to detect uncertainty, but because of a failure to integrate it into output generation. Across architectures, uncertain inputs are reliably identified, occupying…

人工智能 · 计算机科学 2026-03-17 Valeria Ruscio , Keiran Thompson

Large Language Models (LLMs) are powerful and widely adopted, but their practical impact is limited by the well-known hallucination phenomenon. While recent hallucination detection methods have made notable progress, we find most of them…

计算与语言 · 计算机科学 2026-04-21 Boshui Chen , Zhaoxin Fan , Ke Wang , Zhiying Leng , Faguo Wu , Hongwei Zheng , Yifan Sun , Wenjun Wu

Recent advancements in Multimodal Large Language Models (MLLMs) have extended their capabilities to video understanding. Yet, these models are often plagued by "hallucinations", where irrelevant or nonsensical content is generated,…

计算机视觉与模式识别 · 计算机科学 2024-06-25 Yuxuan Wang , Yueqian Wang , Dongyan Zhao , Cihang Xie , Zilong Zheng

While Large Language Models (LLMs) have emerged as powerful foundational models to solve a variety of tasks, they have also been shown to be prone to hallucinations, i.e., generating responses that sound confident but are actually incorrect…

计算与语言 · 计算机科学 2026-04-29 Jiawei Li , Akshayaa Magesh , Venugopal V. Veeravalli

Large language models (LLMs) have transformed natural language processing, achieving remarkable performance across diverse tasks. However, their impressive fluency often comes at the cost of producing false or fabricated information, a…

计算与语言 · 计算机科学 2026-03-20 Aisha Alansari , Hamzah Luqman

Large language models (LLMs) have demonstrated remarkable capabilities, but they still frequently produce hallucinations. These hallucinations are difficult to detect in reasoning-intensive tasks, where the content appears coherent but…

计算与语言 · 计算机科学 2026-05-13 Rui Min , Tianyu Pang , Chao Du , Minhao Cheng , Yi R. Fung

Large Vision Language Models (LVLMs) have demonstrated remarkable capabilities in understanding and describing visual content, achieving state-of-the-art performance across various vision-language tasks. However, these models often generate…

计算机视觉与模式识别 · 计算机科学 2025-03-27 Kazi Hasan Ibn Arif , Sajib Acharjee Dip , Khizar Hussain , Lang Zhang , Chris Thomas

Large Language Models (LLMs) often produce fluent yet factually incorrect statements-a phenomenon known as hallucination-posing serious risks in high-stakes domains. We present Layer-wise Semantic Dynamics (LSD), a geometric framework for…

计算与语言 · 计算机科学 2025-10-07 Amir Hameed Mir

Large language models (LLMs) produce systematically misleading outputs, from hallucinated citations to strategic deception of evaluators, yet these phenomena are studied by separate communities with incompatible terminology. We propose a…

计算机与社会 · 计算机科学 2026-04-07 Jerick Shi , Terry Jingcheng Zhang , Zhijing Jin , Vincent Conitzer

This research paper focuses on the challenges posed by hallucinations in large language models (LLMs), particularly in the context of the medical domain. Hallucination, wherein these models generate plausible yet unverified or incorrect…

计算与语言 · 计算机科学 2023-10-17 Ankit Pal , Logesh Kumar Umapathi , Malaikannan Sankarasubbu

Large Vision Language Models (LVLMs) have shown remarkable capabilities in multimodal tasks like visual question answering or image captioning. However, inconsistencies between the visual information and the generated text, a phenomenon…

计算机视觉与模式识别 · 计算机科学 2025-03-26 Laura Fieback , Jakob Spiegelberg , Hanno Gottschalk