中文
相关论文

相关论文: Shaking to Reveal: Perturbation-Based Detection of…

200 篇论文

Large Language Models (LLMs) are prone to generating plausible yet incorrect responses, known as hallucinations. Effectively detecting hallucinations is therefore crucial for the safe deployment of LLMs. Recent research has linked…

计算与语言 · 计算机科学 2026-03-03 Litian Liu , Reza Pourreza , Sunny Panchal , Apratim Bhattacharyya , Yubing Jian , Yao Qin , Roland Memisevic

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

The detection of sophisticated hallucinations in Large Language Models (LLMs) is hampered by a ``Detection Dilemma'': methods probing internal states (Internal State Probing) excel at identifying factual inconsistencies but fail on logical…

计算与语言 · 计算机科学 2026-01-09 Yusheng Song , Lirong Qiu , Xi Zhang , Zhihao Tang

Large language models (LLMs) have demonstrated strong mathematical reasoning capabilities but remain susceptible to hallucinations producing plausible yet incorrect statements especially in theorem proving, symbolic manipulation, and…

人工智能 · 计算机科学 2025-06-23 MingShan Liu , Jialing Fang

The proliferation of Large Language Models (LLMs) is challenged by hallucinations, critical failure modes where models generate non-factual, nonsensical or unfaithful text. This paper introduces Semantic Divergence Metrics (SDM), a novel…

计算与语言 · 计算机科学 2025-08-15 Igor Halperin

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…

计算与语言 · 计算机科学 2026-05-28 Yuang Huang , Yafeng Zhang , Yu Zilan

This project develops a self correcting framework for large language models (LLMs) that detects and mitigates hallucinations during multi-step reasoning. Rather than relying solely on final answer correctness, our approach leverages fine…

人工智能 · 计算机科学 2025-11-21 Chelsea Zou , Yiheng Yao , Basant Khalil

Large language models (LLMs) hallucinate with confidence: their outputs can be fluent, authoritative, and simply wrong. In medical, legal, and scientific applications this failure causes direct harm, and detecting it from internal model…

计算与语言 · 计算机科学 2026-05-19 Khizar Hussain , Murat Kantarcioglu

Large language models (LLMs) are highly capable but face latency challenges in real-time applications, such as conducting online hallucination detection. To overcome this issue, we propose a novel framework that leverages a small language…

计算与语言 · 计算机科学 2024-08-26 Mengya Hu , Rui Xu , Deren Lei , Yaxi Li , Mingyu Wang , Emily Ching , Eslam Kamal , Alex Deng

Detecting hallucinations in large language models (LLMs) remains a fundamental challenge for their trustworthy deployment. Going beyond basic uncertainty-driven hallucination detection frameworks, we propose a simple yet powerful method…

人工智能 · 计算机科学 2025-10-10 Rui Wang , Zeming Wei , Guanzhang Yue , Meng Sun

Despite substantial advances, large language models (LLMs) continue to exhibit hallucinations, generating plausible yet incorrect responses. In this paper, we highlight a critical yet previously underexplored class of hallucinations driven…

计算与语言 · 计算机科学 2025-11-24 Shaowen Wang , Yiqi Dong , Ruinian Chang , Tansheng Zhu , Yuebo Sun , Kaifeng Lyu , Jian Li

Large Language Models (LLMs) have demonstrated remarkable capabilities across a variety of tasks in different domains. However, they sometimes generate responses that are logically coherent but factually incorrect or misleading, which is…

计算与语言 · 计算机科学 2025-05-23 Fujie Zhang , Peiqi Yu , Biao Yi , Baolei Zhang , Tong Li , Zheli Liu

Large language models (LLMs) can suffer from hallucinations when generating text. These hallucinations impede various applications in society and industry by making LLMs untrustworthy. Current LLMs generate text in an autoregressive fashion…

机器学习 · 计算机科学 2025-11-05 Lukas Aichberger , Kajetan Schweighofer , Mykyta Ielanskyi , Sepp Hochreiter

Hallucinations in large language models (LLMs) present a growing challenge across real-world applications, from healthcare to law, where factual reliability is essential. Despite advances in alignment and instruction tuning, LLMs can still…

计算与语言 · 计算机科学 2025-05-02 Makoto Sato

Large Language Models (LLMs) are powerful computational models trained on extensive corpora of human-readable text, enabling them to perform general-purpose language understanding and generation. LLMs have garnered significant attention in…

计算与语言 · 计算机科学 2024-10-28 Liam Barkley , Brink van der Merwe

Hallucinations in Large Language Models (LLMs) pose a major barrier to their reliable use in critical decision-making. Although existing hallucination detection methods have improved accuracy, they still struggle with disentangling semantic…

计算与语言 · 计算机科学 2026-04-02 Junjie Hu , Gang Tu , ShengYu Cheng , Jinxin Li , Jinting Wang , Rui Chen , Zhilong Zhou , Dongbo Shan

Recent advancements in Multimodal Large Language Models (MLLMs) have enabled them to effectively integrate vision and language, addressing a variety of downstream tasks. However, despite their significant success, these models still exhibit…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Zixian Gao , Chao Yang , Zhanhui Zhou , Xing Xu , Chaochao Lu

Large Language Models (LLMs) have succeeded in a variety of natural language processing tasks [Zha+25]. However, they have notable limitations. LLMs tend to generate hallucinations, a seemingly plausible yet factually unsupported output…

计算与语言 · 计算机科学 2025-09-19 Martin Preiß

The performance of Large Language Models (LLMs) relies heavily on the quality of prompts, which are often manually engineered and task-specific, making them costly and non-scalable. We propose a novel approach, Supervisory Prompt Training…

计算与语言 · 计算机科学 2024-03-28 Jean Ghislain Billa , Min Oh , Liang Du

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
‹ 上一页 1 2 3 10 下一页 ›