立即打开
ChatGPT的能力有多强?未来有望给数百万学生做家教

ChatGPT的能力有多强?未来有望给数百万学生做家教

Anne Trumbore, The Conversation 2023-03-11
一款具有高级会话能力的新一代人工智能聊天机器人ChatGPT也许可以胜任家教的角色。

两名学生正在做一个项目。图片来源:WILLIE B. THOMAS—GETTY IMAGES

想象一下这样一个场景,有这样一位私人家教,能够不知疲倦地教学生,可以接触到大量的数据,而且能够为所有人提供免费教育。1966年,斯坦福大学(Stanford University)的哲学教授帕特里克·苏普斯正是这样想的,他做出了这样的预测:有一天,随着计算机技术不断发展,“数以百万计的学童”将有机会得到私人家教的指导。他说,这种情况就像当时还是年轻王子的亚历山大大帝接受亚里士多德的辅导一样。

现在,一款具有高级会话能力的新一代人工智能聊天机器人ChatGPT也许可以胜任家教的角色。ChatGPT已经收集了大量关于各种主题的数据,而且还能够通过研究生考试。作为一名研究如何利用计算机帮助人们学习的研究人员,我认为ChatGPT可以用来帮助学生在学业上取得优异成绩。但是,就其目前的形式而言,ChatGPT无法专注于某一特定的任务,更不用说辅导了。

早在20世纪90年代互联网成为全球商业网络之前,哲学、工程和人工智能学者就设想过让计算机充当“智能家教”。我相信开发这些早期辅导系统的经验教训能够为学生和教育工作者在未来如何更好地利用ChatGPT充当家教带来启示。

计算机充当家教

斯坦福大学的哲学教授苏普斯是“计算机辅助教学”领域的先驱。他开发了一些最早的教育软件。该软件可以为学生提供个人指导,与那些没有使用该软件的学生相比,使用了该软件的学生能够取得更优异的成绩。从2004年到2012年,我在苏普斯手底下工作,负责开发软件和其他在线程序。

从那时起,推出为学生提供辅导的“智能家教”的实验推动了人工智能、社交网络和计算机硬件的发展。如今,ChatGPT可以写论文、回答哲学问题和解决计算机编码问题,最终可能实现苏普斯提供个性化辅导的目标。

早期版本的个性化学习系统

1972年,一款名为PLATO的新型个性化学习系统问世。PLATO是自动化教学操作的程序逻辑(Programmed Logic for Automated Teaching Operations)的首字母缩写。这是同类产品中第一款广泛使用的个性化学习系统。

PLATO是由伊利诺伊大学(University of Illinois)的电气工程教授唐·比泽尔创建的,允许多达1,000名学生同时登录到一台大型计算机上。每名学生都能够完成外语、音乐、数学和许多其他科目的不同在线课程,同时获得计算机对他们作业的反馈。

PLATO使学生在更短的时间内达到与面授课程学生相同的成绩水平。而且大多数学生更喜欢这种教学模式,而不是坐在大课堂里。然而,该系统过于昂贵,许多学院和大学都无法使用。每台计算机终端的售价超过8,000美元,相当于今天的5.8万美元,而且每次学生使用该系统时,学校都要收取额外费用。尽管如此,PLATO取得的成功激发了许多公司开发提供类似辅导的软件,包括由苏普斯共同创立的College Curriculum Corporation。

流行的个人计算机品牌,例如苹果(Apple)和康懋达(Commodore),宣传内置的教育软件,成为家庭投资家用计算机的一大缘由。

到1985年,卡内基梅隆大学(Carnegie Mellon University)的研究人员利用人工智能和认知心理学方面取得的进展设计了新软件。他们声称,目前的技术已经发展到这样的水平,计算机系统可以像人类家教一样为学生提供高效辅导。然而,尽管当时有超过10,000款教育软件可供选择,但其中大部分软件的质量相当差强人意,并不能够提供真正的辅导。

尽管卡内基梅隆大学开发的更先进的教育软件使学生可以比传统教室里的学生学得更多,但它们并没有在学校得到广泛使用。

在20世纪80年代和90年代,一所学校需要相当数量的昂贵的高性能计算机工作站,以便学生能够使用“智能家教”。今天,计算机功能更强大,价格也更便宜。

早期的“智能家教”主要用于数学、科学和技术课程,这使得它们吸引力有限。学生不能向软件程序提问。然而,学生可以得到关于测验和测试的反馈。

2001年,下一代智能家教系统能够与学生进行书面英语对话。这些系统是早期的聊天机器人,利用自然语言处理方面取得的进展与学生就一系列主题进行对话。每个系统都是专门为某一门学科设计的,比如物理学。增加另一门学科,例如英语,将需要设计英语方面的专门辅导系统。

接下来的几年中,在三大方面取得的进展使得实现计算机教学的梦想有了飞跃。一是宽带网络的出现,它比20世纪90年代的拨号连接更快。其次是功能更强大的计算机的成本更低。第三是科技公司的投资和政府对大学人工智能研究的资助,促进了我们现在称之为聊天机器人的发展。

第一批聊天机器人

到2007年,早期的人工智能聊天机器人通过回答学生问题来提供辅导。研究表明,在这些聊天机器人的辅导下,学生可以取得类似于人类家教辅导的学习成果。即便如此,使用聊天机器人技术提供辅导主要还是实验性的。

在21世纪10年代,社交网络和人工智能的进步极大地改变了人们与技术互动的方式。聊天机器人已经融入了我们生活的方方面面,不再是实验性的了。现在人们与手机、汽车和家用电器对话。很多人家里都有虚拟助手。他们能够向Alexa、Siri或谷歌(Google)问路,或者是问它们简单的家庭作业问题。

如今,ChatGPT有更高级的功能,可以进行更复杂的对话,还能够提供个性化辅导,就像苏普斯在1966年预测的那样。

我问ChatGPT为什么它可以成为优秀的家教,它回答说:“我之所以能够成为好家教,是因为我可以理解各种问题,并根据提示给出答案。针对各种主题,我都能够提供准确而详实的信息。此外,我还可以用清晰易懂的方式传达这些信息,这样不同理解水平的学生都能够理解我的回答。而且,因为我是机器学习模型,可以在较短时间内提供大量有效信息,这对那些试图在短时间内学习大量新资料的学生来说大有裨益。”

相比之下,Siri说:“嗯……我没有办法回答这个问题。还有什么我能够帮助你的吗?”

最近在大学课程中使用聊天机器人的研究表明,使用聊天机器人对鼓励学生进行更深入地学习很重要。比如,在卡内基梅隆大学的云计算研究生课程中,人工智能聊天机器人使学生的学习效果得到了显著改善。当这些聊天机器人要求学生在现有论点的基础上进行论证,或者就他们已经提出的观点提供更多信息时,学生们的学习效果得到了很大提升。在这种情况下,聊天机器人向学生提问,而不是回答学生的提问。

许多教育工作者担心学生使用ChatGPT后学习效果会下降,因为用它可以在作业和论文中作弊。其他人则担心ChatGPT会给出错误答案或传播错误信息。

然而,智能家教的历史和研究表明,只要正确使用 ChatGPT等聊天机器人,几乎所有人都能够进行更深入地个性化学习。例如,如果人们使用ChatGPT向学生提问,促使他们修改或解释自己的作业,学生将可以提高学习成绩。由于ChatGPT所能接触到的知识比亚里士多德所能接触到的要多得多,因此它在为学生提供辅导方面有很大的潜力,可以帮助学生学到更多的知识。(财富中文网)

安妮·特朗博(Anne Trumbore)是弗吉尼亚大学桑兹终身学习研究所(Sands Institute for Lifelong Learning at the University of Virginia)的首席数字学习官。

译者:中慧言-王芳

想象一下这样一个场景,有这样一位私人家教,能够不知疲倦地教学生,可以接触到大量的数据,而且能够为所有人提供免费教育。1966年,斯坦福大学(Stanford University)的哲学教授帕特里克·苏普斯正是这样想的,他做出了这样的预测:有一天,随着计算机技术不断发展,“数以百万计的学童”将有机会得到私人家教的指导。他说,这种情况就像当时还是年轻王子的亚历山大大帝接受亚里士多德的辅导一样。

现在,一款具有高级会话能力的新一代人工智能聊天机器人ChatGPT也许可以胜任家教的角色。ChatGPT已经收集了大量关于各种主题的数据,而且还能够通过研究生考试。作为一名研究如何利用计算机帮助人们学习的研究人员,我认为ChatGPT可以用来帮助学生在学业上取得优异成绩。但是,就其目前的形式而言,ChatGPT无法专注于某一特定的任务,更不用说辅导了。

早在20世纪90年代互联网成为全球商业网络之前,哲学、工程和人工智能学者就设想过让计算机充当“智能家教”。我相信开发这些早期辅导系统的经验教训能够为学生和教育工作者在未来如何更好地利用ChatGPT充当家教带来启示。

计算机充当家教

斯坦福大学的哲学教授苏普斯是“计算机辅助教学”领域的先驱。他开发了一些最早的教育软件。该软件可以为学生提供个人指导,与那些没有使用该软件的学生相比,使用了该软件的学生能够取得更优异的成绩。从2004年到2012年,我在苏普斯手底下工作,负责开发软件和其他在线程序。

从那时起,推出为学生提供辅导的“智能家教”的实验推动了人工智能、社交网络和计算机硬件的发展。如今,ChatGPT可以写论文、回答哲学问题和解决计算机编码问题,最终可能实现苏普斯提供个性化辅导的目标。

早期版本的个性化学习系统

1972年,一款名为PLATO的新型个性化学习系统问世。PLATO是自动化教学操作的程序逻辑(Programmed Logic for Automated Teaching Operations)的首字母缩写。这是同类产品中第一款广泛使用的个性化学习系统。

PLATO是由伊利诺伊大学(University of Illinois)的电气工程教授唐·比泽尔创建的,允许多达1,000名学生同时登录到一台大型计算机上。每名学生都能够完成外语、音乐、数学和许多其他科目的不同在线课程,同时获得计算机对他们作业的反馈。

PLATO使学生在更短的时间内达到与面授课程学生相同的成绩水平。而且大多数学生更喜欢这种教学模式,而不是坐在大课堂里。然而,该系统过于昂贵,许多学院和大学都无法使用。每台计算机终端的售价超过8,000美元,相当于今天的5.8万美元,而且每次学生使用该系统时,学校都要收取额外费用。尽管如此,PLATO取得的成功激发了许多公司开发提供类似辅导的软件,包括由苏普斯共同创立的College Curriculum Corporation。

流行的个人计算机品牌,例如苹果(Apple)和康懋达(Commodore),宣传内置的教育软件,成为家庭投资家用计算机的一大缘由。

到1985年,卡内基梅隆大学(Carnegie Mellon University)的研究人员利用人工智能和认知心理学方面取得的进展设计了新软件。他们声称,目前的技术已经发展到这样的水平,计算机系统可以像人类家教一样为学生提供高效辅导。然而,尽管当时有超过10,000款教育软件可供选择,但其中大部分软件的质量相当差强人意,并不能够提供真正的辅导。

尽管卡内基梅隆大学开发的更先进的教育软件使学生可以比传统教室里的学生学得更多,但它们并没有在学校得到广泛使用。

在20世纪80年代和90年代,一所学校需要相当数量的昂贵的高性能计算机工作站,以便学生能够使用“智能家教”。今天,计算机功能更强大,价格也更便宜。

早期的“智能家教”主要用于数学、科学和技术课程,这使得它们吸引力有限。学生不能向软件程序提问。然而,学生可以得到关于测验和测试的反馈。

2001年,下一代智能家教系统能够与学生进行书面英语对话。这些系统是早期的聊天机器人,利用自然语言处理方面取得的进展与学生就一系列主题进行对话。每个系统都是专门为某一门学科设计的,比如物理学。增加另一门学科,例如英语,将需要设计英语方面的专门辅导系统。

接下来的几年中,在三大方面取得的进展使得实现计算机教学的梦想有了飞跃。一是宽带网络的出现,它比20世纪90年代的拨号连接更快。其次是功能更强大的计算机的成本更低。第三是科技公司的投资和政府对大学人工智能研究的资助,促进了我们现在称之为聊天机器人的发展。

第一批聊天机器人

到2007年,早期的人工智能聊天机器人通过回答学生问题来提供辅导。研究表明,在这些聊天机器人的辅导下,学生可以取得类似于人类家教辅导的学习成果。即便如此,使用聊天机器人技术提供辅导主要还是实验性的。

在21世纪10年代,社交网络和人工智能的进步极大地改变了人们与技术互动的方式。聊天机器人已经融入了我们生活的方方面面,不再是实验性的了。现在人们与手机、汽车和家用电器对话。很多人家里都有虚拟助手。他们能够向Alexa、Siri或谷歌(Google)问路,或者是问它们简单的家庭作业问题。

如今,ChatGPT有更高级的功能,可以进行更复杂的对话,还能够提供个性化辅导,就像苏普斯在1966年预测的那样。

我问ChatGPT为什么它可以成为优秀的家教,它回答说:“我之所以能够成为好家教,是因为我可以理解各种问题,并根据提示给出答案。针对各种主题,我都能够提供准确而详实的信息。此外,我还可以用清晰易懂的方式传达这些信息,这样不同理解水平的学生都能够理解我的回答。而且,因为我是机器学习模型,可以在较短时间内提供大量有效信息,这对那些试图在短时间内学习大量新资料的学生来说大有裨益。”

相比之下,Siri说:“嗯……我没有办法回答这个问题。还有什么我能够帮助你的吗?”

最近在大学课程中使用聊天机器人的研究表明,使用聊天机器人对鼓励学生进行更深入地学习很重要。比如,在卡内基梅隆大学的云计算研究生课程中,人工智能聊天机器人使学生的学习效果得到了显著改善。当这些聊天机器人要求学生在现有论点的基础上进行论证,或者就他们已经提出的观点提供更多信息时,学生们的学习效果得到了很大提升。在这种情况下,聊天机器人向学生提问,而不是回答学生的提问。

许多教育工作者担心学生使用ChatGPT后学习效果会下降,因为用它可以在作业和论文中作弊。其他人则担心ChatGPT会给出错误答案或传播错误信息。

然而,智能家教的历史和研究表明,只要正确使用 ChatGPT等聊天机器人,几乎所有人都能够进行更深入地个性化学习。例如,如果人们使用ChatGPT向学生提问,促使他们修改或解释自己的作业,学生将可以提高学习成绩。由于ChatGPT所能接触到的知识比亚里士多德所能接触到的要多得多,因此它在为学生提供辅导方面有很大的潜力,可以帮助学生学到更多的知识。(财富中文网)

安妮·特朗博(Anne Trumbore)是弗吉尼亚大学桑兹终身学习研究所(Sands Institute for Lifelong Learning at the University of Virginia)的首席数字学习官。

译者:中慧言-王芳

Imagine a private tutor that never gets tired, has access to massive amounts of data and is free for everyone. In 1966, Stanford philosophy professor Patrick Suppes did just that when he made this prediction: One day, computer technology would evolve so that “millions of schoolchildren” would have access to a personal tutor. He said the conditions would be just like the young prince Alexander the Great being tutored by Aristotle.

Now, ChatGPT, a new artificial intelligence-powered chatbot with advanced conversational abilities, may have the capability to become such a tutor. ChatGPT has collected huge amounts of data on a wide range of topics and can pass graduate school exams. As a researcher who studies how computers can be used to help people learn, I think ChatGPT can be used to help students excel academically. However, in its current form, ChatGPT shows an inability to stay focused on one particular task, let alone tutoring.

Philosophy, engineering and artificial intelligence scholars envisioned using the computer as an “intelligent tutor” well before the internet became a global commercial network in the 1990s. I believe lessons from developing those early tutoring systems can offer insight into how students and educators can best make use of ChatGPT as a tutor in the future.

Computers as tutors

Suppes – the Stanford philosophy professor – was a pioneer of a field called “computer-assisted instruction.” He developed some of the earliest educational software. That software provided individual instruction via computer and led students to have better test results than those who didn’t use the program. I worked for Suppes in developing software and other online programs from 2004 to 2012.

Since then, experiments in building “intelligent tutors” to help students have driven advances in artificial intelligence, social networks and computer hardware. And today, the abilities of ChatGPT to write essays, answer philosophical questions and solve computer coding problems may finally achieve Suppes’ goal of truly personalized tutoring via computer.

Early versions of personalized learning

In 1972, a new personalized learning system called PLATO, for Programmed Logic for Automated Teaching Operations, made its debut. It was the first widely available personalized learning system of its kind.

Created by Don Bitzer, a professor of electrical engineering at the University of Illinois, PLATO allowed up to 1,000 students to be logged onto a mainframe computer simultaneously. Each student could complete different online courses in foreign languages, music, math and many other subjects while receiving feedback from the computer on their work.

PLATO enabled students to reach the same level of achievement as in-person classes in less time. And most students preferred this mode of instruction over sitting in a large lecture class. Yet, the system was too expensive to be used by many colleges and universities. Each computer terminal was marketed at over US$8,000 – about $58,000 today – and schools were charged additional fees every time a student used the system. Still, PLATO’s success with students inspired a number of companies to create software that provided a similar kind of tutoring, including the College Curriculum Corporation, which was co-founded by Suppes.

Popular personal computer brands, such as Apple and Commodore, advertised the availability of educational software as a reason for families to invest in a home computer.

By 1985, researchers at Carnegie Mellon University were designing software using advances in artificial intelligence and cognitive psychology. They claimed that the current technology had advanced to a level that enabled computer systems to be designed to serve as effective as human tutors. However, even though there were over 10,000 pieces of educational software available at the time, much of it was of fairly low quality and did not provide real tutoring.

Although the more advanced designs of the educational software developed at Carnegie Mellon enabled students to learn significantly more than students in traditional classrooms, they were not widely used in schools.

In the 1980s and 1990s, a school would need a sizable number of expensive, high-powered computer workstations for students to use an intelligent tutor. Today, the computers are much more powerful and much less expensive.

And early intelligent tutors were used primarily in math, science and technology courses, which limited their appeal. Students could not ask the software programs a question. However, students could get feedback on answers to quizzes and tests.

In 2001, the next generation of intelligent tutoring systems was able to have conversations with students in written English. These systems, early chatbots, used advances in natural language processing to have dialogues with students about a range of subjects. Each system was designed specifically for one subject, such as physics. Adding another subject, like English, would require its own specialized tutoring system.

The next few years brought three developments, which enabled a forward leap in achieving the dream of computerized tutoring. One was the availability of broadband internet, which was faster than the dial-up connections of the 1990s. The second was the lower cost of more powerful computers. The third was investment by technology companies and government funding for university research in artificial intelligence, which led to the development of what we now call chatbots.

The first chatbots

By 2007, early AI chatbots provided tutoring by talking students through their answers to questions. Research showed these chatbots supported learning outcomes similar to the effects of human tutors. Even so, using chatbot technology to provide tutoring was primarily experimental.

During the 2010s, social networks and advances in artificial intelligence dramatically changed the way people interact with technology. Chatbots are integrated into many parts of our lives and are no longer experimental. People now talk to their phones, to their cars and their home appliances. Many people have virtual assistants at home. They can ask Alexa, Siri or Google for directions or the answers to simple homework questions.

Today, ChatGPT has advanced abilities that enable more complex conversations and can provide individualized tutoring much like what Suppes predicted in 1966.

I asked ChatGPT why it would be a good tutor, and it responded: “I am a good tutor for a student because I am able to understand and respond to a wide range of questions and prompts, and I can provide detailed and accurate information on a wide range of subjects. Additionally, I am able to communicate this information in a clear and easy-to-understand manner, making it accessible for students of all levels of understanding. Because I am a machine-learning model, I can also provide a large amount of information quickly and efficiently, which can be especially helpful for students who are trying to learn a lot of new material in a short amount of time.”

By contrast, Siri said, “Hmm … I don’t have an answer for that. Is there something else I can help you with?”

Recent research in using chatbots in college courses shows that how chatbots are used is important in encouraging students to learn more deeply. For instance, AI chatbots enabled significant improvements in learning in a graduate course on cloud computing at Carnegie Mellon. These learning gains occurred when these chatbots asked students to build on an existing argument or to provide more information about a claim they had made. In this case, the chatbot asked the student a question, rather than vice versa.

Many educators are worried about students learning less with ChatGPT since it can be used to cheat on assignments and papers. Others are worried about ChatGPT giving wrong answers or spreading misinformation.

Yet the history and research of intelligent tutors show that using the right design to harness the power of chatbots like ChatGPT can make deeper, individualized learning available to almost anyone. For example, if people use ChatGPT to ask students questions that prompt them to revise or explain their work, students will have better learning gains. Since ChatGPT has access to far more knowledge than Aristotle ever did, it has great potential for providing tutoring to students to help them learn more than they would otherwise.

Anne Trumbore is the chief digital learning officer for the Sands Institute for Lifelong Learning at the University of Virginia.

热读文章
热门视频
扫描二维码下载财富APP