“ChatGPT will redefine the future of academic research. But most academics don’t know how to use it intelligently,” Mushtaq Bilal, a postdoctoral researcher at the University of Southern Denmark, recently tweeted.
Academia and artificial intelligence (AI) are becoming increasingly intertwined, and as AI continues to advance, it is likely that academics will continue to either embrace its potential or voice concerns about its risks.
“There are two camps in academia. The first is the early adopters of artificial intelligence, and the second is the professors and academics who think AI corrupts academic integrity,” Bilal told Euronews Next.
He places himself firmly in the first camp.
The Pakistani-born and Denmark-based professor believes that if used thoughtfully, AI language models could help democratise education and even give way to more knowledge.
Many experts have pointed out that the accuracy and quality of the output produced by language models such as ChatGPT are not trustworthy. The generated text can sometimes be biased, limited or inaccurate.
But Bilal says that understanding those limitations, paired with the right approach, can make language models “do a lot of quality labour for you,” notably for academia.
Incremental prompting to create a ‘structure’
To create an academia-worthy structure, Bilal says it is fundamental to master incremental prompting, a technique traditionally used in behavioural therapy and special education.
It involves breaking down complex tasks into smaller, more manageable steps and providing prompts or cues to help the individual complete each one successfully. The prompts then gradually become more complicated.
In behavioural therapy, incremental prompting allows individuals to build their sense of confidence. In language models, it allows for “way more sophisticated answers”.
In a Twitter thread, Bilal showed how he managed to get ChatGPT to provide a “brilliant outline” for a journal article using incremental prompting.
In his demonstration, Bilal started by asking ChatGPT about specific concepts relevant to his work, then about authors and their ideas, guiding the AI-driven chatbot through the contextual knowledge pertinent to his essay.
“Now that ChatGPT has a fair idea about my project, I ask it to create an outline for a journal article,” he explained, before declaring the results he obtained would likely save him “20 hours of labour”.
“If I just wrote a paragraph for every point in the outline, I’d have a decent first draft of my article”.
Incremental prompting also allows ChatGPT and other AI models to help when it comes to “making education more democratic,” Bilal said.
Some people have the luxury of discussing with Harvard or Oxford professors potential academic outlines or angles for scientific papers, “but not everyone does,” he explained.
“If I were in Pakistan, I would not have access to Harvard professors but I would still need to brainstorm ideas. So instead, I could use AI apps to have an intelligent conversation and help me formulate my research”.
Bilal recently made ChatGPT think and talk like a Stanford professor. Then, to fact-check how authentic the output was, he asked the same questions to a real-life Stanford professor. The results were astonishing.
ChatGPT is only one of the many AI-powered apps you can use for academic writing, or to mimic conversations with renowned academics.
Here are other AI-driven software to help your academic efforts, handpicked by Bilal.
1. Consensus
In Bilal’s words: “If ChatGPT and Google Scholar got married, their child would be Consensus — an AI-powered search engine”.
Consensus looks like most search engines but what sets it apart is that you ask Yes/No questions, to which it provides answers with the consensus of the academic community.
Users can also ask Consensus about the relationship between concepts and about something’s cause and effect. For example: Does immigration improve the economy?
Consensus would reply to that question by stating that most studies have found that immigration generally improves the economy, while also providing a list of the academic papers it used to arrive at the consensus, and ultimately sharing the summaries of the top articles it analysed.
The AI-powered search engine is only equipped to respond on six topics: economics, sleep, social policy, medicine, and mental health and health supplements.
2. Elicit.org
Elicit, “the AI research assistant” according to its founders, also uses language models to answer questions, but its knowledge is solely based on research, enabling “intelligent conversations” and brainstorming with a very knowledgeable and verified source.
The software can also find relevant papers without perfect keyword matches, summarise them and extract key information.
3. Scite.ai
Although language models like ChatGPT are not designed to intentionally deceive, it has been proven they can generate text that is not based on factual information, and include fake citations to papers that don’t exist.
But there is an AI-powered app that gives you real citations to actually published papers – Scite.
“This is one of my favourite ones to improve workflows,” said Bilal.
Similar to Elicit, upon being asked a question, Scite delivers answers with a detailed list of all the papers cited in the response.
“Also, if I make a claim and that claim has been refuted or corroborated by various people or various journals, Scite gives me the exact number. So this is really very, very powerful”.
“If I were to teach any seminar on writing, I would teach how to use this app”.
4. Research Rabbit
“Research Rabbit is an incredible tool that FAST-TRACKS your research. Best part: it’s FREE. But most academics don’t know about it,” tweeted Bilal.
Called by its founders “the Spotify of research,” Research Rabbit allows adding academic papers to “collections”.
These collections allow the software to learn about the user’s interests, prompting new relevant recommendations.
Research Rabbit also allows visualising the scholarly network of papers and co-authorships in graphs, so that users can follow the work of a single topic or author and dive deeper into their research.
- ChatPDF
ChatPDF is an AI-powered app that makes reading and analysing journal articles easier and faster.
“It’s like ChatGPT, but for research papers,” said Bilal.
Users start by uploading the research paper PDF into the AI software and then start asking it questions.
The app then prepares a short summary of the paper and provides the user with examples of questions that it could answer based on the full article.
What promise does AI hold for the future of research?
The development of AI will be as fundamental “as the creation of the microprocessor, the personal computer, the Internet, and the mobile phone,” wrote Bill Gates in the latest post on his personal blog, titled ‘The Age of AI Has Begun’.
“Computers haven’t had the effect on education that many of us in the industry have hoped,” he wrote.
“But I think in the next five to 10 years, AI-driven software will finally deliver on the promise of revolutionising the way people teach and learn”.
