Could AI Help You Write Your Next Paper
by iSophist · 5 things on Twos
- Tools come from natural language processing (NLP), an area of artificial intelligence aimed at helping computers to ‘understand' and even produce human-readable text. Called large language models (LLMs), these tools have evolved to become not only objects of study but also assistants in research.
- Some researchers use LLMs to generate paper titles or to make text more readable. Mina Lee, a doctoral student in computer science at Stanford University, California, gives GPT-3 prompts such as using these keywords, generate the title of a paper.
- OpenAI researchers trained GPT-3 on a vast assortment of text, including books, news stories, Wikipedia entries and software code. The researchers created a fine-tuned version of the algorithm called Codex, training it on more than 150 gigabytes of text from GitHub1.
- AI2's Semantic Scholar search engine covers around 200 million papers. It provides tweet-length descriptions of papers using a language model called TLDR. Elicit uses tools including GPT-3 to extract or generate information from papers.
- Hutson, M. (2022). Could AI help you to write your next paper? Nature, 611(7934), 192–193. https://doi.org/10.1038/d41586-022-03479-w