Using GenAI tools effectively requires that the user know the right questions to ask, and how to phrase them for the best results. Vague or generic questions generate vague or generic results. (In other words you get out of it what you put into it.)
Tips for crafting prompts to get the best results from chatbots:
Western Libraries Catalog Access Permalink Here
The CLEAR framework, created by Librarian Leo S. Lo at the University of New Mexico, is a framework to optimize prompts given to generative AI tools. To follow the CLEAR framework, prompts must be:
Adjust and improve your approach and prompt to the AI tool by evaluating the performance of the AI based on your own assessments of the answers it gives.
Lo, L. S. (2023). The CLEAR path: A framework for enhancing information literacy through prompt engineering. The Journal of Academic Librarianship, 49(4), 102720–. https://doi.org/10.1016/j.acalib.2023.102720
|
Aspect of KS process
|
Possibilities |
Challenges |
|
Literature Review
|
Summarizes large volumes of research quickly, identifying key themes and gaps |
May miss relevant studies by way of hallucinated or misinterpreted summaries
|
|
Data Extraction
|
Automates pulling data from articles (e.g., PICO elements, outcomes) |
Inconsistent accuracy - the need for human validation |
|
Clinical Appraisal
|
Can assist in identifying study design, sample size, risk of bias indicators |
Lacks nuance in evaluating study quality or context |
|
Evidence Mapping
|
Organizes findings into conceptual frameworks or evidence tables |
May impose biased structures due to imitation in interpreting complex relationships
|
|
Writing & Drafting
|
Generates first drafts of synthesis reports, abstracts, or summaries |
Potential for plagiarism. Over-reliance on AI tools may reduce researcher engagement
|
|
Collaboration & Efficiency
|
Speeds up team workflows, supports multilingual synthesis and accessibility |
Tool access may vary across institutions which raises questions about authorship and credit |
Decision Matrix - Top-rated AI tools compared
Monash Health. (2024). AI Search Tools. Monash Health Library Guides. Retrieved April 8, 2025, from https://monashhealth.libguides.com/ld.php?content_id=51696062
Examples:
Claude - this AI chatbot is designed to be more ethical and safer to use than other chatbots and may be more suitable for users who are concerned about chatbots doing objectionable things
ChatGPT 4.0 - ChatGPT is a LLM trained to interact in a conversational way. The dialogue format makes it possible for ChatGPT to answer follow-up questions admit its mistakes, challenge incorrect premises, and reject inappropriate requests.
Perplexity AI This is an AI powered search engine that provides concise answers using web-based resources. Use this to generate terms, become familiar with your new topics, or to ask questions about your research
LitMaps Using a single relevant paper, locate other articles of interest and generate a visual literature map to explore for your literature review
AI Reviewer Provides feedback similar to peer-reviewer. Use when you have a draft manuscript and want feedback before submitting your research to a journal
Anne O’Tate - an integrated, generic tool for summarization, drill-down and browsing of PubMed search results that accommodates a wide range of biomedical users and needs. More about the software here
Gemini - formerly known as Bard, Google Gemini also offers a paid option called Gemini Advanced. Gemini features multimodality and performance, handling various input formats like text, code, audio, and video
VosViewer - used for constructing & visualizing bibliometric networks. These networks may for instance include journals, researchers, or individual publications, and they can be constructed based on citation, bibliographic coupling, co-citation, or co-authorship relations. VOSviewer also offers text mining functionality that can be used to construct and visualize co-occurrence networks of important terms extracted from a body of scientific literature
MeSHonDemand - MeSH on Demand is a tool developed by the National Library of Medicine (NLM). It helps users identify Medical Subject Heading (MeSH) terms relevant to their submitted text
Carrot2 This group of text clustering and visualization tools identifies themes in search results and organizes them into thematic groups
Open Assistant - a free, independent, uncensored chatbot has fewer guardrails and may respond more freely to questions than more conventional bots.
Examples:
2D Search - 2Dsearch is a radical alternative to conventional 'advanced search'. Instead of entering Boolean strings into one-dimensional search boxes, queries are formulated by manipulating objects on a two-dimensional canvas
AI Researcher - simply pose a question, and AI Researcher will delve into an extensive library of textbooks, pinpointing the most relevant works and specific passages that directly address your research query
Consensus - is a search engine that uses AI to extract and distill findings directly from scientific research. It reads the papers for you and extracts key results
AskYourPDF - upload documents into this tool and it will allow you to chat with them and ask questions of them
ASReview Lab - helps with conducting systematic reviews by searching for & identifying the most relevant records by screening large amounts of text
Dimensions AI - database provides free access to over 100 million publications and preprints to help you find exactly what you need, quickly and easily. It also shows the context - with citations, news and social media mentions, and links to funded grants and patents
Inciteful - provides related papers to key articles and illustrates how different papers are related to one another through the literature. Especially helpful for multi-disciplinary research
Research Rabbit - is an innovative “citation-based literature mapping tool" that allows you to supply a seed paper and find more papers relevant to the topic of interest
EvidenceHunt This tool provides a chat-interface to assist users in locating clinical and biomedical evidence
Citation Chaser This package contains functions to automate citation chaining by making use of the Lens.org API. An input article list can be used to return a list of all referenced records, and/or all citing records in the Lens.org database (consisting of PubMed, PubMed Central, CrossRef, Microsoft Academic Graph and CORE)
AI Reviewer provides feedback similar to a peer-reviewer. Use when you have a draft manuscript and want feedback before submitting your research to a journal
Open Assistant This free, independent, uncensored chatbot has fewer guardrails and may respond more freely to questions than more conventional bots.
Scispace This AI program decodes research papers to help you read and understand scientific literature faster. Highlight confusing text, math, and tables to get a simple explanation. Ask follow-up questions and get instant answers. SciSpace Literature Review is also worth trying: https://typeset.io/search
Elicit: The AI Research Assistant Elicit uses language models to help automate research workflows, like parts of a literature review. Elicit can find relevant papers without perfect keyword match, summarize takeaways from the paper specific to your question, and extract key information from the papers. While answering questions with research is the main focus of Elicit, there are also other research tasks that help with brainstorming, summarization, and text classification
Open Scholar - combines cutting-edge retrieval systems with a fine-tuned language model to deliver citation-backed, comprehensive answers to complex research questions
