Skip to main content

How Consensus Works

Allison Elechko avatar
Written by Allison Elechko
Updated over a month ago

What is Consensus?

Consensus is an AI-powered academic search engine built on a database of over 220 million peer-reviewed research papers. Unlike general AI tools, every response is tied back to a real research paper and is grounded in scientific research. It helps you quickly review the literature and understand complex topics faster.

Over 5 million researchers, students, and professionals around the world already trust Consensus to help with their research. It offers a faster, more helpful experience and replaces traditional tools like PubMed and Google Scholar.

Consensus includes AI features like Pro Analysis and Ask Paper, which make academic content more digestible by summarizing and synthesizing research findings. It also offers tools to enhance your literature review workflow, including advanced search filters and the ability to save/organize papers into lists.


What does Consensus search over?

Consensus searches across a database of over 220 million peer-reviewed research papers.

Our paper data comes from trusted sources, including:

Consensus covers all domains and fields of science - from Astronomy to Sociology to Biochemistry! We include papers from most major academic journals, including all of PubMed. The database is updated weekly, as we are always working to expand our coverage and include the latest research.


How does a Consensus search work?

Consensus is designed to find the most relevant scientific papers for your results and ground our AI-generated summaries. Every search goes through three key stages:

Step 1: Cast a wide-net

We begin by scanning our entire database of over 220 million paper to find the most relevant results using a hybrid approach:

  • Semantic search (AI embeddings): Captures the intent behind your search and supports natural language queries.

  • Keyword search (BM25): A traditional method that anchors results to the exact terms in your query for precise keyword matching.

These methods work together to assign a relevance score to each paper by comparing your query to the titles and abstracts in the database. This helps surface papers that match your exact words, while understanding what you're really looking for.

Step 2: Refine by Quality

Next, we take the top 1,500 most relevant papers and re-rank them based on key research quality signals:

  • Recency of publication

  • Citation count

  • Journal impact and reputation

This step ensures your results are highly relevant and back by high-quality, credible science.

Step 3: Rank the top 20 papers

In this final step, we rank the top 20 papers as accurately as possible. This works similar to Step 2, but includes two key upgrades:

  • Relevance is recalculated using a larger, more powerful AI model

  • This high-precision model is applied only to the top 20 papers to ensure efficiency and accuracy

We continue to factor in recency, citation count, and journal impact, so the final list reflects both relevance and rigor.


Key Features

🧠 Pro Analysis: Summaries key findings from the top papers in your search and provides a high level synthesis with citations.

📂 Save Lists: Organize and save papers into custom lists so you can easily revisit and manage your research.

📊 Consensus Meter: Uses AI to analyze and visualize the level of agreement or disagreement in the literature in response to yes-or-no questions.

🔍 Advanced Search Filters: Refine your search using AI-powered filters to surface more relevant and tailored results.

💬 Ask Paper: Chat directly with the full text of a paper to receive in-depth answers about its methods, findings, and more.


How Consensus uses AI responsibly

We are committed to using AI ethically, transparently, and with purpose. Always in service of helping researchers, students, and educators save time without sacrificing trust and accuracy.

We only use AI after we search the scientific literature.

This ensures that every response is grounded in real, citable research, not speculative content generated by a model.

Once relevant papers are retrieved, we use AI in two key ways:

  1. To analyze individual papers in depth (e.g. Ask Paper, Study Snapshot)

  2. To synthesize findings across multiple papers (e.g. Pro Analysis, Consensus Meter)

Generative AI is a powerful tool that can help us reclaim valuable time to focus on what matters most - which is why, at Consensus, we've built in safeguards to ensure it's used responsibly and effectively.


Who made Consensus?

The Consensus team! Read more about who’s on the team here. Christian Salem and Eric Olson are the Co-founders of Consensus.

The Consensus mission is to make the world’s best information accessible to everyone.

Find the best science, faster, with Consensus.


Is there any information we missed? Email us with your feedback!

Did this answer your question?