中文
相关论文

相关论文: An Analysis of Decoding Methods for LLM-based Agen…

200 篇论文

As large language models (LLMs) perform more difficult tasks, it becomes harder to verify the correctness and safety of their behavior. One approach to help with this issue is to prompt LLMs to externalize their reasoning, e.g., by having…

Large Language Models (LLMs) are widely used in critical fields such as healthcare, education, and finance due to their remarkable proficiency in various language-related tasks. However, LLMs are prone to generating factually incorrect…

Despite their impressive capabilities, large language models (LLMs) are prone to hallucinations, i.e., generating content that deviates from facts seen during pretraining. We propose a simple decoding strategy for reducing hallucinations…

计算与语言 · 计算机科学 2024-03-12 Yung-Sung Chuang , Yujia Xie , Hongyin Luo , Yoon Kim , James Glass , Pengcheng He

While large language models exhibit remarkable performance in the Question Answering task, they are susceptible to hallucinations. Challenges arise when these models grapple with understanding multi-hop relations in complex questions or…

计算与语言 · 计算机科学 2023-11-14 Hejing Cao , Zhenwei An , Jiazhan Feng , Kun Xu , Liwei Chen , Dongyan Zhao

Agents equipped with search tools have emerged as effective solutions for knowledge-intensive tasks. While Large Language Models (LLMs) exhibit strong reasoning capabilities, their high computational cost limits practical deployment for…

人工智能 · 计算机科学 2026-04-07 Yizhou Liu , Qi Sun , Yulin Chen , Siyue Zhang , Chen Zhao

Fact-seeking question answering with large language models (LLMs) remains unreliable when answers depend on up-to-date or conflicting information. Although retrieval-augmented and tool-using LLMs reduce hallucinations, they often rely on…

计算与语言 · 计算机科学 2026-03-17 Auksarapak Kietkajornrit , Jad Tarifi , Nima Asgharbeygi

Large Language Models (LLMs) have transformed natural language processing (NLP) tasks, but they suffer from hallucination, generating plausible yet factually incorrect content. This issue extends to Video-Language Models (VideoLLMs), where…

计算机视觉与模式识别 · 计算机科学 2025-04-22 Ahmad Khalil , Mahmoud Khalil , Alioune Ngom

Despite their remarkable capabilities, Large Language Models (LLMs) are prone to generate responses that contradict verifiable facts, i.e., unfaithful hallucination content. Existing efforts generally focus on optimizing model parameters or…

计算与语言 · 计算机科学 2025-01-28 Dingkang Yang , Dongling Xiao , Jinjie Wei , Mingcheng Li , Zhaoyu Chen , Ke Li , Lihua Zhang

Grounding responses in external knowledge represents an effective strategy for mitigating hallucinations in Large Language Models (LLMs). However, current LLMs struggle to seamlessly integrate knowledge while simultaneously maintaining…

计算与语言 · 计算机科学 2025-08-27 Chenxu Yang , Qingyi Si , Zheng Lin

Hallucinations in large language models (LLMs), defined as fluent yet incorrect or incoherent outputs, pose a significant challenge to the automatic generation of educational multiple-choice questions (MCQs). We identified four key…

计算与语言 · 计算机科学 2026-01-22 Nicholas X. Wang , Aggelos K. Katsaggelos

Large Language Models (LLMs) often hallucinate, producing unfaithful or factually incorrect outputs by misrepresenting the provided context or incorrectly recalling internal knowledge. Recent studies have identified specific attention heads…

Large Language Models (LLMs) enhanced with retrieval, an approach known as Retrieval-Augmented Generation (RAG), have achieved strong performance in open-domain question answering. However, RAG remains prone to hallucinations: factually…

Recent advances in large language models (LLMs) have significantly improved multi-hop question answering (QA) through direct Chain-of-Thought (CoT) reasoning. However, the irreversible nature of CoT leads to error accumulation, making it…

人工智能 · 计算机科学 2025-05-30 Xinjie Zhao , Fan Gao , Xingyu Song , Yingjian Chen , Rui Yang , Yanran Fu , Yuyang Wang , Yusuke Iwasawa , Yutaka Matsuo , Irene Li

Large language models (LLMs) have demonstrated remarkable performance on various natural language processing tasks. However, they are prone to generating fluent yet untruthful responses, known as "hallucinations". Hallucinations can lead to…

计算与语言 · 计算机科学 2024-06-18 Minda Hu , Bowei He , Yufei Wang , Liangyou Li , Chen Ma , Irwin King

Large language models (LLMs) have shown substantial capacity for generating fluent, contextually appropriate responses. However, they can produce hallucinated outputs, especially when a user query includes one or more false premises-claims…

计算与语言 · 计算机科学 2026-02-18 Yuehan Qin , Shawn Li , Yi Nian , Xinyan Velocity Yu , Yue Zhao , Xuezhe Ma

Ensuring truthfulness in large language models (LLMs) remains a critical challenge for reliable text generation. While supervised fine-tuning and reinforcement learning with human feedback have shown promise, they require a substantial…

机器学习 · 计算机科学 2026-03-17 Manh Nguyen , Sunil Gupta , Hung Le

Hallucination, the generation of factually incorrect information, remains a significant challenge for large language models (LLMs), especially in open-domain long-form generation. Existing approaches for detecting hallucination in long-form…

The integration of Large Language Models (LLMs) into various applications has driven the need for structured and reliable responses. A key challenge in Retrieval-Augmented Generation (RAG) systems is ensuring that outputs align with…

计算与语言 · 计算机科学 2025-09-09 Özgür Uğur , Musa Yılmaz , Esra Şavirdi , Özay Ezerceli , Mahmut El Huseyni , Selva Taş , Reyhan Bayraktar

LLMs have shown the capacity to improve their performance on reasoning tasks through reflecting on their mistakes, and acting with these reflections in mind. However, continual reflections of the same LLM onto itself exhibit degeneration of…

人工智能 · 计算机科学 2025-12-25 Onat Ozer , Grace Wu , Yuchen Wang , Daniel Dosti , Honghao Zhang , Vivi De La Rue

Knowledge gaps and hallucinations are persistent challenges for Large Language Models (LLMs), which generate unreliable responses when lacking the necessary information to fulfill user instructions. Existing approaches, such as…

计算与语言 · 计算机科学 2025-11-20 Riccardo Pozzi , Matteo Palmonari , Andrea Coletta , Luigi Bellomarini , Jens Lehmann , Sahar Vahdati
‹ 上一页 1 2 3 10 下一页 ›