对于广泛的NLG问题中的幻觉问题定义如下:the generated content that is nonsensical or unfaithful to the provided source content。 幻觉问题可以分为两类:内在幻觉和外在幻觉(intrinsic hallucination and extrinsic hallucination)。内在幻觉指的是输出内容和源输入内容不符,例如输出了错误的年份信息、人名信息等;外在...
Survey of Hallucination in Natural Language Generationarxiv.org/abs/2202.03629 笔者也整理了一些相关的最新工作(主要是大模型相关),在如下仓库: Reading list of hallucination in LLMs.github.com/HillZhang1999/llm-hallucination-survey 幻觉的定义 定义:当模型生成的文本不遵循原文(Faithfulness)或者不符合...
在自然语言处理领域，研究者观察到自然语言生成（NLG）模型的训练目标可能引发生成结果的缺陷，导致输出显得乏味、不连贯或陷入循环。同时，模型有时会生成无意义的文本或与提供的输入信息不符，这一现象被称为幻觉问题（hallucination）。本文从幻觉问题出发，探讨不同任务下的具体问题，如抽象总结、对话生成...
Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of sequence-to-sequence deep learning technologies such as Transformer-based language models. This advancement has led to more fluent and coherent NLG, leading to improved development in downstream task...
Survey of Hallucination in Natural Language Generation. arXiv 2022 paper bib Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Yejin Bang, Andrea Madotto, Pascale Fung Survey of the State of the Art in Natural Language Generation: Core tasks, applications and...
UINav: A maker of UI automation agents. [paper] UI自动化的基准测试 Mapping natural language commands to web elements. [EMNLP 2018] [paper][code] UIBert: Learning Generic Multimodal Representations for UI Understanding. [IJCAI-21] [paper] ...
Survey of Hallucination in Natural Language Generation. [ACM Computing Surveys 2023] [paper] A Survey of Hallucination in Large Foundation Models. [arXiv, 2023] [paper] DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agents. [arXiv, 2023] [paper] Cumulative Reasoning...
The emergence of large language models (LLMs) has marked a significant breakthrough in natural language processing (NLP), fueling a paradigm shift in information acquisition. Nevertheless, LLMs are prone to hallucination, generating plausible yet nonfactual content. This phenomenon raises significant co...
Hallucination是文本生成中一个非常独特的存在。有些人试图解决它,有些人认为根本不可能被解决,有些人选择利用他,而更多人可能目前只是无视他,就像无视了the elephant in the room。《Can We Catch the Elephant? A Survey of the Evolvement of Hallucination Evaluation on Natural Language Generation》这篇论文对...
[1] Yinheng Li, Shaofei Wang, Han Ding, and Hang Chen. Large language models in finance: Asurvey. In Proceedings of the Fourth ACM International Conference on AI in Finance, pages374–382, 2023. 这篇论文聚焦于大语言模型在金融领域的运用。