Although generative AI chatbots can deliver answers to questions in a way that feels similar to a traditional search engine, such as Google, it's important to understand that these tools operate very differently from the search engines and retrieval systems that we're used to.
tl;dr: Gemini, ChatGPT, and Claude are not search engines!
Compare the following:
One key element of genAI "search" is whether this specific model/version of genAI is connected to the live/open internet. Some AI chatbots and new search tools have real-time access to the Internet, and will incorporate search results into their generated responses. These systems work by using AI to transform a question into a set of queries used to search the Internet, and then generate a text-based response based on the information that it finds. This approach is known as "Retrieval Augmented Generation," or RAG. RAG and similar technologies are used to in tools like Perplexity, Google AI overviews, and many other AI-driven search applications.
This does not mean genAI tools can't be useful for you in searching for information, however! Below are some strategies for using genAI more effectively for searching and discovering information.
While finding a source you can cite and use is usually the end result of your search strategy, you can actually break your search into several steps:
The research process is highly iterative, and generative chatbots provide an open and creative space to explore ideas, learn about topics that are entirely new to you, generate research questions, and discover new directions of interest. When you have a new assignment, and don't know where to begin, asking an LLM to summarize the current state of research on a topic may be just what you need to begin the brainstorming process.
Highly niche or emerging fields and technologies. The training data for most LLMs is no longer transparently reported, so users don't have key information needed to know if the information you see is up to date.
A key skill to develop as a strategic researcher is the ability to brainstorm effective search terms, including synonyms. When you are starting to research a new topic, it can be difficult to brainstorm synonyms, phrases or terms of art that are likely to appear in the sources you most want to find.
Prompting strategy: ask a chatbot for a list of synonyms, similar concepts, phrases, theories, or methods the next time you begin a new research project!
Still want to use a chatbot for general search? Just use caution given the limited scope and discoverability issues, as described above.
There are a number of tools that are specifically designed to summarize articles or other documents. Many of these are fee-based tools that are designed to help students and researchers generate summaries of articles and other readings without having to read the full document. These tools can be useful for managing a large number of articles when you need a basic familiarity with their contents, but in most situations you should fully read sources when you need a deep understanding of the material.
You can also use most AI tools, including ChatGPT, Google Gemini, and NotebookLM to summarize readings for you by pasting in the text or uploading a file and asking for a summary. You can give additional prompts to refine the summary, such as asking the chatbot to assume a certain level of knowledge on the part of the reader ("Explain it as if I'm 12 years old...") or to focus on specific information ("Summarize the methods section...").
It is important to remember that these tools are not actually reading or understanding the documents that you give it, and the summary will be influenced by the dataset that the AI tool was trained on. Before using an AI tool in this way, try testing it out with some readings that you know and understand very well, to get a sense of the quality of the summary.
Generative AI chatbots don't refer to, quote from, or recall information from specific or actual sources. A generative AI chatbot (like Gemini, ChatGPT, Claude, etc.) will generate sources or appear to cite sources if you ask it to, but it's important to keep in mind that it does not actually "read" or "understand" these sources. In some situations, the chatbot will make up entirely fake citations.
When using any of the generative AI chatbots for your research, it is essential to develop your fact-checking skills, including tracing claims, locating original sources, and verifying citations or 'cited' content in the generated response. Depending on the nature of the information you need to verify, you may be able to do this with Google, but when using chatbots for academic research, you may need to use library resources if the information is 'coming' from an academic journal article, for example. Always trace the claim to the original source before using it in your own work.
In addition to the more well-known chatbots, there are new and specialized AI-driven research tools being developed and deployed. Some of these are integrated into traditional library research databases, while others are standalone products. Many, but not all, of these tools require a paid subscription. The quality and capability of these tools varies widely, but some of them show distinct promise as aids in the research process.
The Generative AI Product Tracker lists generative AI products that are aimed at the higher education market, and is a useful resource for learning about new AI tools. If you have questions about these tools, please get in touch with the Library!
Brown University Library | Providence, RI 02912 | (401) 863-2165 | Contact | Comments | Library Feedback | Site Map