Consensus is an academic search engine, powered by AI, but grounded in scientific research. We use language models (LLMs) and purpose-built search technology (Vector search) to surface the most relevant papers. We synthesize both topic-level and paper-level insights. Everything is connected to real research papers.

Consensus provides powerful tools to elevate your research: the Consensus Meter lets you quickly see scientific consensus and gain contextual insights, while Pro Analysis allows you to customize searches to draft content, format text, create lists, and explore topic-based syntheses.

Consensus also offers several other academic features, including advanced search filters by study design, sample size, and methodology. It also provides paper-level insights, study snapshots, quality indicators, auto-citations, and CSV export options to help researchers find, analyze, and organize relevant studies efficiently.

200+ million research papers

The current source material used in Consensus comes from the Semantic Scholar database, which includes over 200 million papers across all domains of science. We continue to add more data over time and our dataset is updated monthly.

We run a custom fine-tuned language model over our entire corpus of research papers and extract the Key Takeaway from every paper. We then remove things like ‘what’, ‘is’, and ‘are’ from the query and run a combination of keyword search + Vector search over the abstract and title of all our papers. This gives us a very intelligent measure of the relevance of a research paper to your query.

This relevance score is then combined with many other pieces of metadata including but not limited to citation count, velocity of citations, study design, and publish date to re-rank the results and produce a top 10 possible results to surface.

When you input a question or a phrase (i.e. the benefits of mindfulness), we then run a custom fine-tuned language model that generates a question-relevant conclusion based on the user query and the abstract of the given paper. For every other type of search, we use the Key Takeaway that we extracted already.

This is the final order in which the research paper results appear on the results page. With this new list of 10 results (either the generated conclusion or the Key Takeaway), we run a final custom fine-tuned language model built for question and answering that ranks the results according to how well they address the user’s query.

🔍 Search Filters: Filter by sample size, study design, methodology, if the paper is open access, a human or animal study (and many more filters).

✨ Paper-level insights: We extract key insights and answers. Locate the most helpful papers and digest their insights faster.

🧑🏽‍🤝‍🧑🏽 Study Snapshot: Our Study Snapshot quickly shows key information like Population, Sample size, Methods, etc. – all within the results page.

🥇 Quality indicators: Focus on the best papers – intuitive labels for citations, journal quality, and study type.

🎓 Auto-citations: Consensus auto-creates citations in multiple formats, we also integrate with Zotero, Paperpile, & soon Endnote!

💻 CSV Export: Export search results (and soon Lists) to CSV. Includes 11 paper-level detail columns & the paper’s link.

📋 Lists & Bookmarks: Stay organized, and save lists of papers or whole searches. Export search results (+paper-level details) to CSV.

Consensus Pro Analysis brings ChatGPT-type functionality to Consensus. Along with your search, you can have Pro answer questions, draft content, create lists, and more. Just tell Pro what to do along with your query. Learn more about Pro Analysis here.

Unlike generative LLMs like ChatGPT, Pro is connected to the science. Each number refers to the research paper that the information is drawn from. Click on the number in Pro and you’ll drop down to the research paper on your results page.

For a question or a phrase search, with enough relevant results, we then run OpenAI’s GPT-4 large language model over it. The top 10 results produce a simple one-sentence summary of the top studies to your question. This generated summary can be seen in the Summary box above your search results when Pro is turned off. Learn more about the Summary feature here.

If you have input a yes/no question into the search engine, with enough relevant results, we then run a custom fine-tuned LLM that classifies the results as suggesting either “yes”, “no” or “possibly” to your question. The aggregated results of this model can be seen in the Consensus Meter on the top of the results page. Learn more about the Consensus Meter here.

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.

This page was created based on feedback from Consensus users.

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