As Natural Language Processing(NLP)continues to advance,driven by the emergence of sophisticated large language models such as ChatGPT,there has been a notable growth in research activity.This rapid uptake reflects in...As Natural Language Processing(NLP)continues to advance,driven by the emergence of sophisticated large language models such as ChatGPT,there has been a notable growth in research activity.This rapid uptake reflects increasing interest in the field and induces critical inquiries into ChatGPT’s applicability in the NLP domain.This review paper systematically investigates the role of ChatGPT in diverse NLP tasks,including information extraction,Name Entity Recognition(NER),event extraction,relation extraction,Part of Speech(PoS)tagging,text classification,sentiment analysis,emotion recognition and text annotation.The novelty of this work lies in its comprehensive analysis of the existing literature,addressing a critical gap in understanding ChatGPT’s adaptability,limitations,and optimal application.In this paper,we employed a systematic stepwise approach following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses(PRISMA)framework to direct our search process and seek relevant studies.Our review reveals ChatGPT’s significant potential in enhancing various NLP tasks.Its adaptability in information extraction tasks,sentiment analysis,and text classification showcases its ability to comprehend diverse contexts and extract meaningful details.Additionally,ChatGPT’s flexibility in annotation tasks reducesmanual efforts and accelerates the annotation process,making it a valuable asset in NLP development and research.Furthermore,GPT-4 and prompt engineering emerge as a complementary mechanism,empowering users to guide the model and enhance overall accuracy.Despite its promising potential,challenges persist.The performance of ChatGP Tneeds tobe testedusingmore extensivedatasets anddiversedata structures.Subsequently,its limitations in handling domain-specific language and the need for fine-tuning in specific applications highlight the importance of further investigations to address these issues.展开更多
大语言模型(large language models,LLMs)所展现的处理各种自然语言处理(natural language processing,NLP)任务的能力引发了广泛关注.然而,它们在处理现实中各种复杂场景时的鲁棒性尚未得到充分探索,这对于评估模型的稳定性和可靠性尤...大语言模型(large language models,LLMs)所展现的处理各种自然语言处理(natural language processing,NLP)任务的能力引发了广泛关注.然而,它们在处理现实中各种复杂场景时的鲁棒性尚未得到充分探索,这对于评估模型的稳定性和可靠性尤为重要.因此,使用涵盖了9个常见NLP任务的15个数据集(约147000个原始测试样本)和来自TextFlint的61种鲁棒的文本变形方法分析GPT-3和GPT-3.5系列模型在原始数据集上的性能,以及其在不同任务和文本变形级别(字符、词和句子)上的鲁棒性.研究结果表明,GPT模型虽然在情感分析、语义匹配等分类任务和阅读理解任务中表现出良好的性能,但其处理信息抽取任务的能力仍较为欠缺,比如其对关系抽取任务中各种关系类型存在严重混淆,甚至出现“幻觉”现象.在鲁棒性评估实验中,GPT模型在任务层面和变形层面的鲁棒性都较弱,其中,在分类任务和句子级别的变形中鲁棒性缺乏更为显著.此外,探究了模型迭代过程中性能和鲁棒性的变化,以及提示中的演示数量和演示内容对模型性能和鲁棒性的影响.结果表明,随着模型的迭代以及上下文学习的加入,模型的性能稳步提升,但是鲁棒性依然亟待提升.这些发现从任务类型、变形种类、提示内容等方面揭示了GPT模型还无法完全胜任常见的NLP任务,并且模型存在的鲁棒性问题难以通过提升模型性能或改变提示内容等方式解决.通过对gpt-3.5-turbo的更新版本、gpt-4模型,以及开源模型LLaMA2-7B和LLaMA2-13B的性能和鲁棒性表现进行对比,进一步验证了实验结论.鉴于此,未来的大模型研究应当提升模型在信息提取以及语义理解等方面的能力,并且应当在模型训练或微调阶段考虑提升其鲁棒性.展开更多
Generative AI,represented by GPT(Generative Pre-trained Transformer),is now leading the technological revolution and is reconstructing the journalism and communication industries'ecosystems because of its powerful...Generative AI,represented by GPT(Generative Pre-trained Transformer),is now leading the technological revolution and is reconstructing the journalism and communication industries'ecosystems because of its powerful generative capacity and diverse range of outputs.While GPT is busy revolutionizing and innovating the production of news content,working patterns,and operation modes,it has also given rise to ethical concerns in regard to news authenticity,data security,humanistic values,and other related aspects.Therefore,it is imperative to initiate strategies and approaches,such as establishing a mechanism for verifying information authenticity,enhancing data security and privacy regulations,and instituting an ethical supervision and governance framework for AI,in order to facilitate the systematic advancement of AI-based news production while reinstating public trust.展开更多
文摘As Natural Language Processing(NLP)continues to advance,driven by the emergence of sophisticated large language models such as ChatGPT,there has been a notable growth in research activity.This rapid uptake reflects increasing interest in the field and induces critical inquiries into ChatGPT’s applicability in the NLP domain.This review paper systematically investigates the role of ChatGPT in diverse NLP tasks,including information extraction,Name Entity Recognition(NER),event extraction,relation extraction,Part of Speech(PoS)tagging,text classification,sentiment analysis,emotion recognition and text annotation.The novelty of this work lies in its comprehensive analysis of the existing literature,addressing a critical gap in understanding ChatGPT’s adaptability,limitations,and optimal application.In this paper,we employed a systematic stepwise approach following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses(PRISMA)framework to direct our search process and seek relevant studies.Our review reveals ChatGPT’s significant potential in enhancing various NLP tasks.Its adaptability in information extraction tasks,sentiment analysis,and text classification showcases its ability to comprehend diverse contexts and extract meaningful details.Additionally,ChatGPT’s flexibility in annotation tasks reducesmanual efforts and accelerates the annotation process,making it a valuable asset in NLP development and research.Furthermore,GPT-4 and prompt engineering emerge as a complementary mechanism,empowering users to guide the model and enhance overall accuracy.Despite its promising potential,challenges persist.The performance of ChatGP Tneeds tobe testedusingmore extensivedatasets anddiversedata structures.Subsequently,its limitations in handling domain-specific language and the need for fine-tuning in specific applications highlight the importance of further investigations to address these issues.
文摘大语言模型(large language models,LLMs)所展现的处理各种自然语言处理(natural language processing,NLP)任务的能力引发了广泛关注.然而,它们在处理现实中各种复杂场景时的鲁棒性尚未得到充分探索,这对于评估模型的稳定性和可靠性尤为重要.因此,使用涵盖了9个常见NLP任务的15个数据集(约147000个原始测试样本)和来自TextFlint的61种鲁棒的文本变形方法分析GPT-3和GPT-3.5系列模型在原始数据集上的性能,以及其在不同任务和文本变形级别(字符、词和句子)上的鲁棒性.研究结果表明,GPT模型虽然在情感分析、语义匹配等分类任务和阅读理解任务中表现出良好的性能,但其处理信息抽取任务的能力仍较为欠缺,比如其对关系抽取任务中各种关系类型存在严重混淆,甚至出现“幻觉”现象.在鲁棒性评估实验中,GPT模型在任务层面和变形层面的鲁棒性都较弱,其中,在分类任务和句子级别的变形中鲁棒性缺乏更为显著.此外,探究了模型迭代过程中性能和鲁棒性的变化,以及提示中的演示数量和演示内容对模型性能和鲁棒性的影响.结果表明,随着模型的迭代以及上下文学习的加入,模型的性能稳步提升,但是鲁棒性依然亟待提升.这些发现从任务类型、变形种类、提示内容等方面揭示了GPT模型还无法完全胜任常见的NLP任务,并且模型存在的鲁棒性问题难以通过提升模型性能或改变提示内容等方式解决.通过对gpt-3.5-turbo的更新版本、gpt-4模型,以及开源模型LLaMA2-7B和LLaMA2-13B的性能和鲁棒性表现进行对比,进一步验证了实验结论.鉴于此,未来的大模型研究应当提升模型在信息提取以及语义理解等方面的能力,并且应当在模型训练或微调阶段考虑提升其鲁棒性.
基金the phased achievement of the subject“Research on Deepening the Construction of‘Smart Chengdu’and Enhancing the Governance Efficiency of Megacities” (2023CS120)a key project under Chengdu’s Philosophy and Social Science Planning Program for 2023。
文摘Generative AI,represented by GPT(Generative Pre-trained Transformer),is now leading the technological revolution and is reconstructing the journalism and communication industries'ecosystems because of its powerful generative capacity and diverse range of outputs.While GPT is busy revolutionizing and innovating the production of news content,working patterns,and operation modes,it has also given rise to ethical concerns in regard to news authenticity,data security,humanistic values,and other related aspects.Therefore,it is imperative to initiate strategies and approaches,such as establishing a mechanism for verifying information authenticity,enhancing data security and privacy regulations,and instituting an ethical supervision and governance framework for AI,in order to facilitate the systematic advancement of AI-based news production while reinstating public trust.
