Skip to Main Content

Consensus AI Research Tool at TMC Library

Consensus Overview

Consensus is an AI search tool specifically focused on academic research content. Use it to search for peer-reviewed literature, not to ask general purpose questions.  It is not a chatbot.  It is a search engine that uses AI to summarize real scientific papers.  But it does not replace your own evidence-based synthesis of research.

Watch the Consensus 101 webinar to learn about what Consensus is and what it does.

(Passcode for webinar if prompted: tD&43$3Q)

Consensus is searching in Semantic Scholar, OpenAlex, and their own "crawl of the scholarly web." Consensus also searches subscription-based content available through the Texas Medical Center (TMC) Library.

 

Consensus pro setting

The default setting is Consensus Pro, to retrieve and analyze 20 papers based on your prompt.

However, users also have access to 50 "Deep searches" per month. Deep searches are more intensive and a bit lengthier, providing a report of the literature on your research question. The report includes a summary, an overview of research gaps, indications of the consensus on the topic across the field, and clickable links to the literature included in the report. 

Sign Up for Consensus

The TMC Library subscribes to the Enterprise version of Consensus, which also provides academic users with unlimited Pro Analyses, unlimited Study Snapshots and unlimited Ask Paper messages.

  • Pro Analyses analyzes up to 20 research papers relevant to a search query. Users can ask for answers is specific formats, such as a bulleted list, comparison table or topic overview.
  • Study Snaphots provide quick summaries of key details from individual research papers, such as population, sample, size, location, methods, outcomes, or other essential information.
  • Ask Paper allows users to ask questions about a single study's methodology, results, charts or complex terms. It  can help researchers understand the technical aspects of a paper, clarifying things such as statistical data, algebra or code.

_________________________________________________________________________________________

Sign up for a Consensus account by using your institutional email address.

When you first sign up for a Consensus account, you will be prompted to confirm that your institution is the Texas Medical Center Library. 

_________________________________________________________________________________________

If you already created a free Consensus account using an institutional email address, you will automatically have access to the Enterprise version of Consensus, and your account will be automatically affiliated with the TMC Library's subscription.

The blue and white icon in the lower left corner of the Consensus page, next to your username, verifies that you have access to the Enterprise level features:

 

Safeguards in Consensus AI searching

How Consensus Handles Hallucinations

Hallucinations are a common issue in AI systems where models generate something that is not true.   

These usually fall into three separate categories:

  • Fake sources - the AI cites a paper or article that doesn't exist.
  • Wrong facts - the AI generates a confident answer from internal memory that's simply incorrect with no source.
  • Misread sources - the AI summaries a real paper or source, cites it, but gets it wrong.

 

Because of how Consensus was built, only the third type of hallucination is possible.

Remember that Consensus isn't a chatbot. It's a search engine that uses AI to summarize real scientific papers. Every time you ask a question, it's searching a database of peer-reviewed research. 

 

https://consensus.app/home/blog/how-consensus works/